%%% -*-BibTeX-*-
%%% ====================================================================
%%%  BibTeX-file{
%%%     author          = "Nelson H. F. Beebe",
%%%     version         = "1.51",
%%%     date            = "24 September 2014",
%%%     time            = "08:13:39 MDT",
%%%     filename        = "vldbj.bib",
%%%     address         = "University of Utah
%%%                        Department of Mathematics, 110 LCB
%%%                        155 S 1400 E RM 233
%%%                        Salt Lake City, UT 84112-0090
%%%                        USA",
%%%     telephone       = "+1 801 581 5254",
%%%     FAX             = "+1 801 581 4148",
%%%     URL             = "http://www.math.utah.edu/~beebe",
%%%     checksum        = "32274 30007 164558 1624938",
%%%     email           = "beebe at math.utah.edu, beebe at acm.org,
%%%                        beebe at computer.org (Internet)",
%%%     codetable       = "ISO/ASCII",
%%%     keywords        = "BibTeX; bibliography; Very Large Data Bases
%%%                        Journal; VLDB Journal",
%%%     license         = "public domain",
%%%     supported       = "yes",
%%%     docstring       = "This is a COMPLETE bibliography of
%%%                        publications in the VLDB journal: Very Large
%%%                        Data Bases (CODEN VLDBFR, ISSN 1066-8888
%%%                        (print), 0949-877X (electronic)), originally
%%%                        published by Springer-Verlag on behalf of the
%%%                        VLDB Endowment, and now published by the ACM.
%%%
%%%                        Publication of the VLDB Journal begain with
%%%                        volume 1, number 1, in 1992, and the journal
%%%                        is normally published quarterly, although
%%%                        occasionally, issues are combined, or volumes
%%%                        are split across year boundaries.
%%%
%%%                        There is an editorial World Wide Web site at
%%%
%%%                            http://SunSITE.Informatik.RWTH-Aachen.DE/dblp/db/journals/vldb/
%%%
%%%                        and publisher Web sites at
%%%
%%%                            http://portal.acm.org/toc.cfm?id=J869
%%%                            http://link.springer.de/link/service/journals/00778/index.htm
%%%
%%%                        At version 1.51, the year coverage looked
%%%                        like this:
%%%
%%%                             1992 (   7)    2000 (  29)    2008 (  68)
%%%                             1993 (  19)    2001 (  25)    2009 (  53)
%%%                             1994 (  22)    2002 (  23)    2010 (  45)
%%%                             1995 (  24)    2003 (  23)    2011 (  41)
%%%                             1996 (  18)    2004 (  23)    2012 (  40)
%%%                             1997 (  22)    2005 (  22)    2013 (  38)
%%%                             1998 (  22)    2006 (  24)    2014 (  28)
%%%                             1999 (  13)    2007 (  26)
%%%
%%%                             Article:        655
%%%
%%%                             Total entries:  655
%%%
%%%                        This bibliography was prepared largely from
%%%                        the Web pages at the editorial and publisher
%%%                        sites.
%%%
%%%                        Spelling has been verified with the UNIX
%%%                        spell and GNU ispell programs using the
%%%                        exception dictionary stored in the companion
%%%                        file with extension .sok.
%%%
%%%                        BibTeX citation tags are uniformly chosen
%%%                        as name:year:abbrev, where name is the
%%%                        family name of the first author or editor,
%%%                        year is a 4-digit number, and abbrev is a
%%%                        3-letter condensation of important title
%%%                        words. Citation tags were automatically
%%%                        generated by software developed for the
%%%                        BibNet Project.
%%%
%%%                        In this bibliography, entries are sorted in
%%%                        publication order within each journal,
%%%                        using bibsort -bypages.
%%%
%%%                        The checksum field above contains a CRC-16
%%%                        checksum as the first value, followed by the
%%%                        equivalent of the standard UNIX wc (word
%%%                        count) utility output of lines, words, and
%%%                        characters.  This is produced by Robert
%%%                        Solovay's checksum utility.",
%%%  }
%%% ====================================================================

@Preamble{
    "\ifx \undefined \ocirc  \def \ocirc #1{{\accent'27#1}}\fi"
}

%%% ====================================================================
%%% Acknowledgement abbreviations:

@String{ack-nhfb = "Nelson H. F. Beebe,
                    University of Utah,
                    Department of Mathematics, 110 LCB,
                    155 S 1400 E RM 233,
                    Salt Lake City, UT 84112-0090, USA,
                    Tel: +1 801 581 5254,
                    FAX: +1 801 581 4148,
                    e-mail: \path|beebe@math.utah.edu|,
                            \path|beebe@acm.org|,
                            \path|beebe@computer.org| (Internet),
                    URL: \path|http://www.math.utah.edu/~beebe/|"}

%%% ====================================================================
%%% Journal abbreviations:

@String{j-VLDB-J = "VLDB Journal: Very Large Data Bases"}

%%% ====================================================================
%%% Bibliography entries, sorted in publication order:

@Article{Breitbart:1992:TMI,
  author =       "Yuri Breitbart and Abraham Silberschatz and Glenn R.
                 Thompson",
  title =        "Transaction Management Issues in a Failure-Prone
                 Multidatabase System Environment",
  journal =      j-VLDB-J,
  volume =       "1",
  number =       "1",
  pages =        "1--39",
  month =        jul,
  year =         "1992",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:23 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb1.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Breitbart:Yuri.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Silberschatz:Abraham.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Thompson:Glenn_R=.html",
  abstract =     "This paper is concerned with the problem of
                 integrating a number of existing, off-the-shelf local
                 database systems into a multidatabase system that
                 maintains consistency in the face of concurrency and
                 failures. The major difficulties in designing such
                 systems stem from the requirements that local
                 transactions be allowed to execute outside the
                 multidatabase system control, and that the various
                 local database systems cannot participate in the
                 execution of a global commit protocol. A scheme based
                 on the assumption that the component local database
                 systems use the strict two-phase locking protocol is
                 developed. Two major problems are addressed: How to
                 ensure global transaction atomicity without the
                 provision of a commit protocol, and how to ensure
                 freedom from global deadlocks.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "algorithms; deadlock recovery; performance;
                 reliability; serializibility; transaction log",
  xxauthor =     "Yuri Breitbart and Avi Silberschatz and Glenn R.
                 Thompson",
  xxpages =      "1--40",
}

@Article{Nodine:1992:CTH,
  author =       "Marian H. Nodine and Stanley B. Zdonik",
  title =        "Cooperative Transaction Hierarchies: Transaction
                 Support for Design Applications",
  journal =      j-VLDB-J,
  volume =       "1",
  number =       "1",
  pages =        "41--80",
  month =        jul,
  year =         "1992",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:23 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb1.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Nodine:Marian_H=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Zdonik:Stanley_B=.html",
  abstract =     "Traditional atomic and nested transactions are not
                 always well-suited to cooperative applications, such as
                 design applications. Cooperative applications place
                 requirements on the database that may conflict with the
                 serializability requirement. They require transactions
                 to be long, possibly nested, and able to interact with
                 each other in a structured way. We define a transaction
                 framework, called a {\em cooperative transaction
                 hierarchy}, that allows us to relax the requirement for
                 atomic, serializable transactions to better support
                 cooperative applications. In cooperative transaction
                 hierarchies, we allow the correctness specification for
                 groups of designers to be tailored to the needs of the
                 application. We use {\em patterns\/} and {\em
                 conflicts\/} to specify the constraints imposed on a
                 group's history for it to be correct. We also provide
                 some primitives to smooth the operation of the members.
                 We characterize deadlocks in a cooperative transaction
                 hierarchy, and provide mechanisms for deadlock
                 detection and resolution. We examine issues associated
                 with failure and recovery.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "cooperation; deadlock detection; design transactions;
                 non-serializability; transaction hierarchies;
                 transaction synchronization; version management",
}

@Article{Spaccapietra:1992:MIA,
  author =       "Stefano Spaccapietra and Christine Parent and Yann
                 Dupont",
  title =        "Model Independent Assertions for Integration of
                 Heterogeneous Schemas",
  journal =      j-VLDB-J,
  volume =       "1",
  number =       "1",
  pages =        "81--126",
  month =        jul,
  year =         "1992",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:23 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb1.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Dupont:Yann.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Parent:Christine.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Spaccapietra:Stefano.html",
  abstract =     "Due to the proliferation of database applications, the
                 integration of existing databases into a distributed or
                 federated system is one of the major challenges in
                 responding to enterprises' information requirements.
                 Some proposed integration techniques aim at providing
                 database administrators (DBAs) with a view definition
                 language they can use to build the desired integrated
                 schema. These techniques leave to the DBA the
                 responsibility of appropriately restructuring schema
                 elements from existing local schemas and of solving
                 inter-schema conflicts. This paper investigates the
                 {\em assertion-based\/} approach, in which the DBA's
                 action is limited to pointing out corresponding
                 elements in the schemas and to defining the nature of
                 the correspondence in between. This methodology is
                 capable of: ensuring better integration by taking into
                 account additional semantic information (assertions
                 about links); automatically solving structural
                 conflicts; building the integrated schema without
                 requiring conforming of initial schemas; applying
                 integration rules to a variety of data models; and
                 performing view as well as database integration. This
                 paper presents the basic ideas underlying our approach
                 and focuses on resolution of structural conflicts.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "conceptual modeling; database design and integration;
                 distributed databases; federated databases;
                 heterogeneous databases; schema integration",
}

@Article{Hsiao:1992:FDSa,
  author =       "David K. Hsiao",
  title =        "Federated Databases and Systems: Part {I} --- {A}
                 Tutorial on Their Data Sharing",
  journal =      j-VLDB-J,
  volume =       "1",
  number =       "1",
  pages =        "127--179",
  month =        jul,
  year =         "1992",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:23 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb1.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Hsiao:David_K=.html",
  abstract =     "The issues and solutions for the interoperability of a
                 class of heterogeneous databases and their database
                 systems are expounded in two parts. Part I presents the
                 data-sharing issues in federated databases and systems.
                 Part II, which will appear in a future issue, explores
                 resource-consolidation issues. {\em Interoperability\/}
                 in this context refers to data sharing among
                 heterogeneous databases, and to resource consolidation
                 of computer hardware, system software, and support
                 personnel. {\em Resource consolidation\/} requires the
                 presence of a database system architecture which
                 supports the heterogeneous system software, thereby
                 eliminating the need for various computer hardware and
                 support personnel. The class of heterogeneous databases
                 and database systems expounded herein is termed {\em
                 federated}, meaning that they are joined in order to
                 meet certain organizational requirements and because
                 they require their respective application
                 specificities, integrity constraints, and security
                 requirements to be upheld. Federated databases and
                 systems are new. While there are no technological
                 solutions, there has been considerable research towards
                 their development. This tutorial is aimed at exposing
                 the need for such solutions. A taxonomy is introduced
                 in our review of existing research undertakings and
                 exploratory developments. With this taxonomy, we
                 contrast and compare various approaches to federating
                 databases and systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "attribute-based;
                 data-model-and-language-to-data-model-and-language
                 mappings; database conversion; hierarchical; network;
                 object-oriented; relational; schema transformation;
                 transaction translation",
  xxpages =      "127--180",
}

@Article{Breitbart:1992:OMT,
  author =       "Yuri Breitbart and Hector Garcia-Molina and Abraham
                 Silberschatz",
  title =        "Overview of Multidatabase Transaction Management",
  journal =      j-VLDB-J,
  volume =       "1",
  number =       "2",
  pages =        "181--240",
  month =        oct,
  year =         "1992",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:23 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb1.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Breitbart:Yuri.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Garcia=Molina:Hector.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Silberschatz:Abraham.html",
  abstract =     "A multidatabase system (MDBS) is a facility that
                 allows users access to data located in multiple
                 autonomous database management systems (DBMSs). In such
                 a system, {\em global transactions\/} are executed
                 under the control of the MDBS. Independently, {\em
                 local transactions\/} are executed under the control of
                 the local DBMSs. Each local DBMS integrated by the MDBS
                 may employ a different transaction management scheme.
                 In addition, each local DBMS has complete control over
                 all transactions (global and local) executing at its
                 site, including the ability to abort at any point any
                 of the transactions executing at its site. Typically,
                 no design or internal DBMS structure changes are
                 allowed in order to accommodate the MDBS. Furthermore,
                 the local DBMSs may not be aware of each other and, as
                 a consequence, cannot coordinate their actions. Thus,
                 traditional techniques for ensuring transaction
                 atomicity and consistency in homogeneous distributed
                 database systems may not be appropriate for an MDBS
                 environment. The objective of this article is to
                 provide a brief review of the most current work in the
                 area of multidatabase transaction management. We first
                 define the problem and argue that the multidatabase
                 research will become increasingly important in the
                 coming years. We then outline basic research issues in
                 multidatabase transaction management and review recent
                 results in the area. We conclude with a discussion of
                 open problems and practical implications of this
                 research.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "multidatabase; recovery; reliability; serializability;
                 transaction; two-level serializability",
  xxauthor =     "Yuri Breitbart and Hector Garcia-Molina and Avi
                 Silberschatz",
}

@Article{Drew:1992:TII,
  author =       "Pamela Drew and Roger King and Dennis Heimbigner",
  title =        "A Toolkit for the Incremental Implementation of
                 Heterogeneous Database Management Systems",
  journal =      j-VLDB-J,
  volume =       "1",
  number =       "2",
  pages =        "241--284",
  month =        oct,
  year =         "1992",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:23 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb1.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Drew:Pamela.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Heimbigner:Dennis.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/King:Roger.html",
  abstract =     "The integration of heterogeneous database environments
                 is a difficult and complex task. The A la carte
                 Framework addresses this complexity by providing a
                 reusable and extensible architecture in which a set of
                 heterogeneous database management systems can be
                 integrated. The goal is to support incremental
                 integration of existing database facilities into
                 heterogeneous, interoperative, distributed systems. The
                 Framework addresses the three main issues in
                 heterogeneous systems integration. First, it identifies
                 the problems in integrating heterogeneous systems.
                 Second, it identifies the key interfaces and parameters
                 required for autonomous systems to interoperate
                 correctly. Third, it demonstrates an approach to
                 integrating these interfaces in an extensible and
                 incremental way. The A la carte Framework provides a
                 set of reusable, integrating components which integrate
                 the major functional domains, such as transaction
                 management, that could or should be integrated in
                 heterogeneous systems. It also provides a mechanism for
                 capturing key characteristics of the components and
                 constraints which describe how the components can be
                 mixed and interchanged, thereby helping to reduce the
                 complexity of the integration process. Using this
                 framework, we have implemented an experimental,
                 heterogeneous configuration as part of the object
                 management work in the software engineering research
                 consortium, Arcadia.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database toolkits; extensible databases; heterogeneous
                 databases; heterogeneous transaction management;
                 incremental integration; open architectures;
                 reconfigurable architectures",
}

@Article{Hsiao:1992:FDSb,
  author =       "David K. Hsiao",
  title =        "Federated Databases and Systems: Part {II} --- {A}
                 Tutorial on Their Resource Consolidation",
  journal =      j-VLDB-J,
  volume =       "1",
  number =       "2",
  pages =        "285--310",
  month =        oct,
  year =         "1992",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:23 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb1.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Hsiao:David_K=.html",
  abstract =     "The issues and solutions for the interoperability of a
                 class of heterogeneous databases and their database
                 systems are expounded in two parts. Part I presented
                 the data-sharing issues in federated databases and
                 systems (Hsiao, 1992). The present article explores
                 resource-consolidation issues. {\em Interoperability\/}
                 in this context refers to data sharing among
                 heterogeneous databases, and to resource consolidation
                 of computer hardware, system software, and support
                 personnel. {\em Resource consolidation\/} requires the
                 presence of a database system architecture which
                 supports the heterogeneous system software, thereby
                 eliminating the need for various computer hardware and
                 support personnel. The class of heterogeneous databases
                 and database systems expounded herein is termed {\em
                 federated}, meaning that they are joined in order to
                 meet certain organizational requirements and because
                 they require their respective application
                 specificities, integrity constraints, and security
                 requirements to be upheld. Federated databases and
                 systems are new. While there are no technological
                 solutions, there has been considerable research towards
                 their development. This tutorial is aimed at exposing
                 the need for such solutions. A taxonomy is introduced
                 in our review of existing research undertakings and
                 exploratory developments. With this taxonomy, we
                 contrast and compare various approaches to federating
                 databases and systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "attribute-based;
                 data-model-and-language-to-data-model-and-language
                 mappings; database conversion; hierarchical; network;
                 object-oriented; relational; schema transformation;
                 transaction translation",
}

@Article{Yu:1993:BMB,
  author =       "Philip S. Yu and Douglas W. Cornell",
  title =        "Buffer Management Based on Return on Consumption in a
                 Multi-Query Environment",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "1",
  pages =        "1--37",
  month =        jan,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:24 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Cornell:Douglas_W=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Yu:Philip_S=.html",
  abstract =     "In a multi-query environment, the marginal utilities
                 of allocating additional buffer to the various queries
                 can be vastly different. The conventional approach
                 examines each query in isolation to determine the
                 optimal access plan and the corresponding locality set.
                 This can lead to performance that is far from optimal.
                 As each query can have different access plans with
                 dissimilar locality sets and sensitivities to memory
                 requirement, we employ the concepts of memory
                 consumption and return on consumption (ROC) as the
                 basis for memory allocations. Memory consumption of a
                 query is its space-time product, while ROC is a measure
                 of the effectiveness of response-time reduction through
                 additional memory consumption. A global optimization
                 strategy using simulated annealing is developed, which
                 minimizes the average response over all queries under
                 the constraint that the total memory consumption rate
                 has to be less than the buffer size. It selects the
                 optimal join method and memory allocation for all query
                 types simultaneously. By analyzing the way the optimal
                 strategy makes memory allocations, a heuristic
                 threshold strategy is then proposed. The threshold
                 strategy is based on the concept of ROC. As the memory
                 consumption rate by all queries is limited by the
                 buffer size, the strategy tries to allocate the memory
                 so as to make sure that a certain level of ROC is
                 achieved. A simulation model is developed to
                 demonstrate that the heuristic strategy yields
                 performance that is very close to the optimal strategy
                 and is far superior to the conventional allocation
                 strategy.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "buffer management; join methods; query optimization;
                 queueing model; simulated annealing; simulation",
  xxpages =      "1--38",
}

@Article{Harder:1993:CCI,
  author =       "Theo H{\"a}rder and Kurt Rothermel",
  title =        "Concurrency Control Issues in Nested Transactions",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "1",
  pages =        "39--74",
  month =        jan,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:24 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/H=auml=rder:Theo.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Rothermel:Kurt.html",
  abstract =     "The concept of nested transactions offers more
                 decomposable execution units and finer-grained control
                 over concurrency and recovery than `flat' transactions.
                 Furthermore, it supports the decomposition of a `unit
                 of work' into subtasks and their appropriate
                 distribution in a computer system as a prerequisite of
                 intratransaction parallelism. However, to exploit its
                 full potential, suitable granules of concurrency
                 control as well as access modes for shared data are
                 necessary. In this article, we investigate various
                 issues of concurrency control for nested transactions.
                 First, the mechanisms for cooperation and communication
                 within nested transactions should not impede parallel
                 execution of transactions among parent and children or
                 among siblings. Therefore, a model for nested
                 transactions is proposed allowing for effective
                 exploitation of intra-transaction parallelism. Starting
                 with a set of basic locking rules, we introduce the
                 concept of `downward inheritance of locks' to make data
                 manipulated by a parent available to its children. To
                 support supervised and restricted access, this concept
                 is refined to `controlled downward inheritance.' The
                 initial concurrency control scheme was based on S-X
                 locks for `flat,' non-overlapping data objects. In
                 order to adjust this scheme for practical applications,
                 a set of concurrency control rules is derived for
                 generalized lock modes described by a compatibility
                 matrix. Also, these rules are combined with a
                 hierarchical locking scheme to improve selective access
                 to data granules of varying sizes. After having tied
                 together both types of hierarchies (transaction and
                 object), it can be shown how `controlled downward
                 inheritance' for hierarchical objects is achieved in
                 nested transactions. Finally, problems of deadlock
                 detection and resolution in nested transactions are
                 considered.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; locking; nested transactions;
                 object hierarchies",
}

@Article{Jensen:1993:UDT,
  author =       "Christian S. Jensen and Leo Mark and Nick Roussopoulos
                 and Timos K. Sellis",
  title =        "Using Differential Techniques to Efficiently Support
                 Transaction Time",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "1",
  pages =        "75--116",
  month =        jan,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:24 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/j/Jensen:Christian_S=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mark:Leo.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Roussopoulos:Nick.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sellis:Timos_K=.html",
  abstract =     "We present an architecture for query processing in the
                 relational model extended with transaction time. The
                 architecture integrates standard query optimization and
                 computation techniques with new differential
                 computation techniques. Differential computation
                 computes a query incrementally or decrementally from
                 the cached and indexed results of previous
                 computations. The use of differential computation
                 techniques is essential in order to provide efficient
                 processing of queries that access very large temporal
                 relations. Alternative query plans are integrated into
                 a state transition network, where the state space
                 includes backlogs of base relations, cached results
                 from previous computations, a cache index, and
                 intermediate results; the transitions include standard
                 relational algebra operators, operators for
                 constructing differential files, operators for
                 differential computation, and combined operators. A
                 rule set is presented to prune away parts of state
                 transition networks that are not promising, and dynamic
                 programming techniques are used to identify the optimal
                 plans from the remaining state transition networks. An
                 extended logical access path serves as a `structuring'
                 index on the cached results and contains, in addition,
                 vital statistics for the query optimization process
                 (including statistics about base relations, backlogs,
                 and queries---previously computed and cached,
                 previously computed, or just previously estimated).",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "efficient query processing; incremental and
                 decremental computation; temporal databases;
                 transaction time",
}

@Article{Haritsa:1993:VBS,
  author =       "Jayant R. Haritsa and Michael J. Carey and Miron
                 Livny",
  title =        "Value-Based Scheduling in Real-Time Database Systems",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "2",
  pages =        "117--152",
  month =        apr,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:25 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Carey:Michael_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Haritsa:Jayant_R=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Livny:Miron.html",
  abstract =     "In a real-time database system, an application may
                 assign a {\em value\/} to a transaction to reflect the
                 return it expects to receive if the transaction commits
                 before its deadline. Most research on real-time
                 database systems has focused on systems where all
                 transactions are assigned the same value, the
                 performance goal being to minimize the number of missed
                 deadlines. When transactions are assigned different
                 values, the goal of the system shifts to maximizing the
                 sum of the values of those transactions that commit by
                 their deadlines. Minimizing the number of missed
                 deadlines becomes a secondary concern. In this article,
                 we address the problem of establishing a priority
                 ordering among transactions characterized by both
                 values and deadlines that results in maximizing the
                 realized value. Of particular interest is the tradeoff
                 established between these values and deadlines in
                 constructing the priority ordering. Using a detailed
                 simulation model, we evaluate the performance of
                 several priority mappings that make this tradeoff in
                 different, but fixed, ways. In addition, a `bucket'
                 priority mechanism that allows the relative importance
                 of values and deadlines to be controlled is introduced
                 and studied. The notion of associating a penalty with
                 transactions whose deadlines are not met is also
                 briefly considered.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "priority and concurrency algorithms; priority mapping;
                 resource and data contention; transaction values and
                 deadlines",
}

@Article{Grant:1993:QLR,
  author =       "John Grant and Witold Litwin and Nick Roussopoulos and
                 Timos K. Sellis",
  title =        "Query Languages for Relational Multidatabases",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "2",
  pages =        "153--171",
  month =        apr,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:25 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Grant:John.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Litwin:Witold.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Roussopoulos:Nick.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sellis:Timos_K=.html",
  abstract =     "With the existence of many autonomous databases widely
                 accessible through computer networks, users will
                 require the capability to jointly manipulate data in
                 different databases. A multidatabase system provides
                 such a capability through a multidatabase manipulation
                 language, such as MSQL. We propose a theoretical
                 foundation for such languages by presenting a
                 multirelational algebra and calculus based on the
                 relational algebra and calculus. The proposal is
                 illustrated by various queries on an example
                 multidatabase. It is shown that properties of the
                 multirelational algebra may be used for optimization
                 and that every multirelational algebra query can be
                 expressed as a multirelational calculus query. The
                 connection between the multirelational languages and
                 MSQL, the multidatabase version of SQL, is also
                 investigated.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "multidatabase; multirelational algebra;
                 multirelational calculus; query optimization",
  xxpages =      "153--172",
}

@Article{Neufeld:1993:GCT,
  author =       "Andrea Neufeld and Guido Moerkotte and Peter C.
                 Lockemann",
  title =        "Generating Consistent Test Data for a Variable Set of
                 General Consistency Constraints",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "2",
  pages =        "173--213",
  month =        apr,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:25 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lockemann:Peter_C=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Moerkotte:Guido.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Neufeld:Andrea.html",
  abstract =     "To address the problem of generating test data for a
                 set of general consistency constraints, we propose a
                 new two-step approach: First the interdependencies
                 between consistency constraints are explored and a
                 generator formula is derived on their basis. During its
                 creation, the user may exert control. In essence, the
                 generator formula contains information to restrict the
                 search for consistent test databases. In the second
                 step, the test database is generated. Here, two
                 different approaches are proposed. The first adapts an
                 already published approach to generating finite models
                 by enhancing it with requirements imposed by test data
                 generation. The second, a new approach, operationalizes
                 the generator formula by translating it into a sequence
                 of operators, and then executes it to construct the
                 test database. For this purpose, we introduce two
                 powerful operators: the generation operator and the
                 test-and-repair operator. This approach also allows for
                 enhancing the generation operators with heuristics for
                 generating facts in a goal-directed fashion. It avoids
                 the generation of test data that may contradict the
                 consistency constraints, and limits the search space
                 for the test data. This article concludes with a
                 careful evaluation and comparison of the performance of
                 the two approaches and their variants by describing a
                 number of benchmarks and their results.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "consistency; design; logic; test data; validation",
  xxpages =      "173--214",
  xxtitle =      "Generating consistent test data: restricting the
                 search space by a generator formula",
}

@Article{Du:1993:SCU,
  author =       "Weimin Du and Ahmed K. Elmagarmid and Won Kim and
                 Omran A. Bukhres",
  title =        "Supporting Consistent Updates in Replicated
                 Multidatabase Systems",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "2",
  pages =        "215--241",
  month =        apr,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:25 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Bukhres:Omran_A=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Du:Weimin.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/e/Elmagarmid:Ahmed_K=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kim:Won.html",
  abstract =     "Replication is useful in multidatabase systems (MDBSs)
                 because, as in traditional distributed database
                 systems, it increases data availability in the presence
                 of failures and decreases data retrieval costs by
                 reading local or close copies of data. Concurrency
                 control, however, is more difficult in replicated MDBSs
                 than in ordinary distributed database systems. This is
                 the case not only because local concurrency controllers
                 may schedule global transactions inconsistently, but
                 also because local transactions (at different sites)
                 may access the same replicated data. In this article,
                 we propose a decentralized concurrency control protocol
                 for a replicated MDBS. The proposed strategy supports
                 prompt and consistent updates of replicated data by
                 both local and global applications without a central
                 coordinator.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; multidatabases; replica control;
                 replicated data management; resolvable conflicts;
                 serializability",
}

@Article{Anonymous:1993:Ca,
  author =       "Anonymous",
  title =        "Column",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "2",
  pages =        "??--??",
  month =        apr,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:25 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Anonymous:1993:Cb,
  author =       "Anonymous",
  title =        "Column",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "2",
  pages =        "??--??",
  month =        apr,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:25 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Tomasic:1993:SIP,
  author =       "Anthony Tomasic and Hector Garcia-Molina",
  title =        "Special Issue in Parallelism in Database Systems:
                 Query Processing and Inverted Indices in Shared-Nothing
                 Document Information Retrieval Systems",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "3",
  pages =        "243--275",
  month =        jul,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:01 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Garcia=Molina:Hector.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tomasic:Anthony.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Tomasic:1993:QPI,
  author =       "Anthony Tomasic and Hector Garcia-Molina",
  title =        "Query processing and inverted indices in shared:
                 nothing text document information retrieval systems",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "3",
  pages =        "243--276",
  month =        jul,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:26 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The performance of distributed text document retrieval
                 systems is strongly influenced by the organization of
                 the inverted text. This article compares the
                 performance impact on query processing of various
                 physical organizations for inverted lists. We present a
                 new probabilistic model of the database and queries.
                 Simulation experiments determine those variables that
                 most strongly influence response time and throughput.
                 This leads to a set of design trade-offs over a wide
                 range of hardware configurations and new parallel query
                 processing strategies.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "file organization; full text information retrieval;
                 inverted file; inverted index; performance; query
                 processing; shared-nothing; striping",
}

@Article{Ziane:1993:PQP,
  author =       "Mikal Ziane and Mohamed Za{\"\i}t and Pascale
                 Borla-Salamet",
  title =        "Parallel Query Processing with Zigzag Trees",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "3",
  pages =        "277--301",
  month =        jul,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:26 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Borla=Salamet:Pascale.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Za=iuml=t:Mohamed.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Ziane:Mikal.html",
  abstract =     "In this article, we describe our approach to the
                 compile-time optimization and parallelization of
                 queries for execution in DBS3 or EDS. DBS3 is a
                 shared-memory parallel database system, while the EDS
                 system has a distributed-memory architecture. Because
                 DBS3 implements a parallel dataflow execution model,
                 this approach applies to both architectures. Using
                 randomized search strategies enables the exploration of
                 a search space large enough to include zigzag trees,
                 which are intermediate between left-deep and right-deep
                 trees. Zigzag trees are shown to provide better
                 response time than right-deep trees in case of limited
                 memory. Performance measurements obtained using the
                 DBS3 prototype show the advantages of zigzag trees
                 under various conditions.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "cost function; fragmentation; pipeline; search space",
  xxpages =      "277--302",
}

@Article{Hua:1993:CDS,
  author =       "Kien A. Hua and Yu-lung Lo and Honesty C. Young",
  title =        "Considering Data Skew Factor in Multi-Way Join Query
                 Optimization for Parallel Execution",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "3",
  pages =        "303--330",
  month =        jul,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:26 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Hua:Kien_A=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lo:Yu=lung.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Young:Honesty_C=.html",
  abstract =     "A consensus on parallel architecture for very large
                 database management has emerged. This architecture is
                 based on a shared-nothing hardware organization. The
                 computation model is very sensitive to skew in tuple
                 distribution, however. Recently, several parallel join
                 algorithms with dynamic load balancing capabilities
                 have been proposed to address this issue, but none of
                 them consider multi-way join problems. In this article
                 we propose a dynamic load balancing technique for
                 multi-way joins, and investigate the effect of load
                 balancing on query optimization. In particular, we
                 present a join-ordering strategy that takes
                 load-balancing issues into consideration. Our
                 performance study indicates that the proposed query
                 optimization technique can provide very impressive
                 performance improvement over conventional approaches.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "load balancing; multi-way join; parallel-database
                 computer; query optimization",
  xxauthor =     "Kien A. Hua and Yo Lung Lo and Honesty C. Young",
}

@Article{Zhang:1993:TGC,
  author =       "Aidong Zhang and Ahmed K. Elmagarmid",
  title =        "A Theory of Global Concurrency Control in
                 Multidatabase Systems",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "3",
  pages =        "331--360",
  month =        jul,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:26 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/e/Elmagarmid:Ahmed_K=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Zhang:Aidong.html",
  abstract =     "This article presents a theoretical basis for global
                 concurrency control to maintain global serializability
                 in multidatabase systems. Three correctness criteria
                 are formulated that utilize the intrinsic
                 characteristics of global transactions to determine the
                 serialization order of global subtransactions at each
                 local site. In particular, two new types of
                 serializability, chain-conflicting serializability and
                 sharing serializability, are proposed and hybrid
                 serializability, which combines these two basic
                 criteria, is discussed. These criteria offer the
                 advantage of imposing no restrictions on local sites
                 other than local serializability while retaining global
                 serializability. The graph testing techniques of the
                 three criteria are provided as guidance for global
                 transaction scheduling. In addition, an optimal
                 property of global transactions for determinating the
                 serialization order of global subtransactions at local
                 sites is formulated. This property defines the upper
                 limit on global serializability in multidatabase
                 systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "chain-conflicting serializability; hybrid
                 serializability; optimality; sharing serializability",
}

@Article{Anonymous:1993:SIP,
  author =       "Anonymous",
  title =        "Special issue in parallelism in database systems",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "3",
  pages =        "??--??",
  month =        jul,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:26 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Srinivasan:1993:PBT,
  author =       "V. Srinivasan and Michael J. Carey",
  title =        "Performance of {B$^+$} tree concurrency control
                 algorithms",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "4",
  pages =        "361--406",
  month =        oct,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:27 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Carey:Michael_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Srinivasan:V=.html",
  abstract =     "A number of algorithms have been proposed to access
                 B$^+$-trees concurrently, but they are not well
                 understood. In this article, we study the performance
                 of various B$^+$-tree concurrency control algorithms
                 using a detailed simulation model of B$^+$-tree
                 operations in a centralized DBMS. Our study covers a
                 wide range of data contention situations and resource
                 conditions. In addition, based on the performance of
                 the set of B$^+$-tree concurrency control algorithms,
                 which includes one new algorithm, we make projections
                 regarding the performance of other algorithms in the
                 literature. Our results indicate that algorithms with
                 updaters that lock-couple using exclusive locks perform
                 poorly as compared to those that permit more optimistic
                 index descents. In particular, the B-link algorithms
                 are seen to provide the most concurrency and the best
                 overall performance. Finally, we demonstrate the need
                 for a highly concurrent long-term lock holding strategy
                 to obtain the full benefits of a highly concurrent
                 algorithm for index operations.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "B+-tree structures; data contention; lock modes;
                 performance; resource conditions; simulation models;
                 workload parameters",
  xxtitle =      "Performance of {B+} Tree Concurrency Algorithms",
}

@Article{Weikum:1993:MLT,
  author =       "Gerhard Weikum and Christof Hasse",
  title =        "Multi-Level Transaction Management for Complex
                 Objects: Implementation, Performance, Parallelism",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "4",
  pages =        "407--453",
  month =        oct,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:27 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Hasse:Christof.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Weikum:Gerhard.html",
  abstract =     "Multi-level transactions are a variant of open-nested
                 transactions in which the subtransactions correspond to
                 operations at different levels of a layered system
                 architecture. They allow the exploitation of semantics
                 of high-level operations to increase concurrency. As a
                 consequence, undoing a transaction requires
                 compensation of completed subtransactions. In addition,
                 multi-level recovery methods must take into
                 consideration that high-level operations are not
                 necessarily atomic if multiple pages are updated in a
                 single subtransaction. This article presents algorithms
                 for multi-level transaction management that are
                 implemented in the database kernel system (DASDBS). In
                 particular, we show that multi-level recovery can be
                 implemented in an efficient way. We discuss performance
                 measurements using a synthetic benchmark for processing
                 complex objects in a multi-user environment. We show
                 that multi-level transaction management can be extended
                 easily to cope with parallel subtransactions within a
                 single transaction. Performance results are presented
                 with varying degrees of inter- and intratransaction
                 parallelism.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "atomicity; complex objects; inter- and
                 intratransaction parallelism; multi-level transactions;
                 performance; persistence; recovery",
  xxpages =      "407--454",
}

@Article{Storey:1993:USR,
  author =       "Veda C. Storey",
  title =        "Understanding Semantic Relationships",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "4",
  pages =        "455--488",
  month =        oct,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:27 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Storey:Veda_C=.html",
  abstract =     "To develop sophisticated database management systems,
                 there is a need to incorporate more understanding of
                 the real world in the information that is stored in a
                 database. Semantic data models have been developed to
                 try to capture some of the meaning, as well as the
                 structure, of data using abstractions such as
                 inclusion, aggregation, and association. Besides these
                 well-known relationships, a number of additional
                 semantic relationships have been identified by
                 researchers in other disciplines such as linguistics,
                 logic, and cognitive psychology. This article explores
                 some of the lesser-recognized semantic relationships
                 and discusses both how they could be captured, either
                 manually or by using an automated tool, and their
                 impact on database design. To demonstrate the
                 feasibility of this research, a prototype system for
                 analyzing semantic relationships, called the Semantic
                 Relationship Analyzer, is presented.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database design; database design systems;
                 entity-relationship model; relational model; semantic
                 relationships",
}

@Article{Tseng:1993:SMS,
  author =       "Frank Shou-Cheng Tseng and Arbee L. P. Chen and W.-P.
                 Yang",
  title =        "Searching a Minimal Semantically-Equivalent Subset of
                 a Set of Partial Values",
  journal =      j-VLDB-J,
  volume =       "2",
  number =       "4",
  pages =        "489--512",
  month =        oct,
  year =         "1993",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:27 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb2.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chen:Arbee_L=_P=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tseng:Frank_Shou=Cheng.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Yang:W==P=.html",
  abstract =     "Imprecise data exist in databases due to their
                 unavailability or to data/schema incompatibilities in a
                 multidatabase system. Partial values have been used to
                 represent imprecise data. Manipulation of partial
                 values is therefore necessary to process queries
                 involving imprecise data. In this article, we study the
                 problem of eliminating redundant partial values that
                 result from a projection on an attribute with partial
                 values. The redundancy of partial values is defined
                 through the interpretation of a set of partial values.
                 This problem is equivalent to searching a minimal
                 semantically-equivalent subset of a set of partial
                 values. A semantically-equivalent subset contains
                 exactly the same information as the original set. We
                 derive a set of useful properties and apply a graph
                 matching technique to develop an efficient algorithm
                 for searching such a minimal subset and therefore
                 eliminating redundant partial values. By this process,
                 we not only provide a concise answer to the user, but
                 also reduce the communication cost when partial values
                 are requested to be transmitted from one site to
                 another site in a distributed environment. Moreover,
                 further manipulation of the partial values can be
                 simplified. This work is also extended to the case of
                 multi-attribute projections.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "bipartite graph; graph matching; imprecise data;
                 minimal elements; multidatabase systems; partial
                 values",
  xxauthor =     "Frank S. C. Tseng and Arbee L. P. Chen and Wei Pang
                 Yang",
}

@Article{Georgakopoulos:1994:CST,
  author =       "Dimitrios Georgakopoulos and Marek Rusinkiewicz and
                 Witold Litwin",
  title =        "Chronological Scheduling of Transactions with Temporal
                 Dependencies",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "1",
  pages =        "1--28",
  month =        jan,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:28 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Georgakopoulos:Dimitrios.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Litwin:Witold.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Rusinkiewicz:Marek.html",
  abstract =     "Database applications often impose temporal
                 dependencies between transactions that must be
                 satisfied to preserve data consistency. The extant
                 correctness criteria used to schedule the execution of
                 concurrent transactions are either time independent or
                 use strict, difficult to satisfy real-time constraints.
                 On one end of the spectrum, serializability completely
                 ignores time. On the other end, deadline scheduling
                 approaches consider the outcome of each transaction
                 execution correct only if the transaction meets its
                 real-time deadline. In this article, we explore new
                 correctness criteria and scheduling methods that
                 capture temporal transaction dependencies and belong to
                 the broad area between these two extreme approaches. We
                 introduce the concepts of {\em succession dependency\/}
                 and {\em chronological dependency\/} and define
                 correctness criteria under which temporal dependencies
                 between transactions are preserved even if the
                 dependent transactions execute concurrently. We also
                 propose a {\em chronological scheduler\/} that can
                 guarantee that transaction executions satisfy their
                 chronological constraints. The advantages of
                 chronological scheduling over traditional scheduling
                 methods, as well as the main issues in the
                 implementation and performance of the proposed
                 scheduler, are discussed.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrent succession; execution correctness; partial
                 rollbacks; synchronization; transaction ordering",
}

@Article{Whang:1994:DMD,
  author =       "Kyu Young Whang and Sang Wook Kim and Gio
                 Wiederhold",
  title =        "Dynamic Maintenance of Data Distribution for
                 Selectivity Estimation",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "1",
  pages =        "29--51",
  month =        jan,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:28 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kim:Sang=Wook.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Whang:Kyu=Young.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Wiederhold:Gio.html",
  abstract =     "We propose a new dynamic method for multidimensional
                 selectivity estimation for range queries that works
                 accurately independent of data distribution. Good
                 estimation of selectivity is important for query
                 optimization and physical database design. Our method
                 employs the multilevel grid file (MLGF) for accurate
                 estimation of multidimensional data distribution. The
                 MLGF is a dynamic, hierarchical, balanced,
                 multidimensional file structure that gracefully adapts
                 to nonuniform and correlated distributions. We show
                 that the MLGF directory naturally represents a
                 multidimensional data distribution. We then extend it
                 for further refinement and present the selectivity
                 estimation method based on the MLGF. Extensive
                 experiments have been performed to test the accuracy of
                 selectivity estimation. The results show that
                 estimation errors are very small independent of
                 distributions, even with correlated and/or highly
                 skewed ones. Finally, we analyze the cause of errors in
                 estimation and investigate the effects of various
                 parameters on the accuracy of estimation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "multidimensional file structure; multilevel grid
                 files; physical database design; query optimization",
}

@Article{Kamel:1994:PBO,
  author =       "Nabil Kamel and Ping Wu and Stanley Y. W. Su",
  title =        "A Pattern-Based Object Calculus",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "1",
  pages =        "53--76",
  month =        jan,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:28 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kamel:Nabil.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Su:Stanley_Y=_W=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Wu:Ping.html",
  abstract =     "Several object-oriented database management systems
                 have been implemented without an accompanying
                 theoretical foundation for constraint, query
                 specification, and processing. The pattern-based object
                 calculus presented in this article provides such a
                 theoretical foundation for describing and processing
                 object-oriented databases. We view an object-oriented
                 database as a network of interrelated classes (i.e.,
                 the intension) and a collection of time-varying object
                 association patterns (i.e., the extension). The object
                 calculus is based on first-order logic. It provides the
                 formalism for interpreting precisely and uniformly the
                 semantics of queries and integrity constraints in
                 object-oriented databases. The power of the object
                 calculus is shown in four aspects. First, associations
                 among objects are expressed explicitly in an
                 object-oriented database. Second, the `nonassociation'
                 operator is included in the object calculus. Third,
                 set-oriented operations can be performed on both
                 homogeneous and heterogeneous object association
                 patterns. Fourth, our approach does not assume a
                 specific form of database schema. A proposed formalism
                 is also applied to the design of high-level
                 object-oriented query and constraint languages.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "association patterns; Object-oriented databases; query
                 expressions; semantic constraints",
}

@Article{Sciore:1994:VCM,
  author =       "Edward Sciore",
  title =        "Versioning and Configuration Management in an
                 Object-Oriented Data Model",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "1",
  pages =        "77--106",
  month =        jan,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:28 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sciore:Edward.html",
  abstract =     "Many database applications require the storage and
                 manipulation of different versions of data objects. To
                 satisfy the diverse needs of these applications,
                 current database systems support versioning at a very
                 low level. This article demonstrates that
                 application-independent versioning can be supported at
                 a significantly higher level. In particular, we extend
                 the EXTRA data model and EXCESS query language so that
                 configurations can be specified conceptually and
                 non-procedurally. We also show how version sets can be
                 viewed multidimensionally, thereby allowing
                 configurations to be expressed at a higher level of
                 abstraction. The resulting model integrates and
                 generalizes ideas in CAD systems, CASE systems, and
                 temporal databases.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "EXTRA/EXCESS data models; generic and specific
                 references; query language; semantically based
                 configuration specifications",
}

@Article{Ramamohanarao:1994:IDD,
  author =       "Kotagiri Ramamohanarao and James Harland",
  title =        "An introduction to deductive database languages and
                 systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "2",
  pages =        "107--122",
  month =        apr,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:29 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Ramamohanarao:1994:SIP,
  author =       "Kotagiri Ramamohanarao and James Harland",
  title =        "Special Issue on Prototypes of Deductive Database
                 Systems: An Introduction to Deductive Database
                 Languages and Systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "2",
  pages =        "107--122",
  month =        apr,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:01 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Harland:James.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ramamohanarao:Kotagiri.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Derr:1994:GND,
  author =       "Marcia A. Derr and Shinichi Morishita and Geoffrey
                 Phipps",
  title =        "The Glue-Nail Deductive Database System: Design,
                 Implementation, and Evaluation",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "2",
  pages =        "123--160",
  month =        apr,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:29 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Derr:Marcia_A=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Morishita:Shinichi.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Phipps:Geoffrey.html",
  abstract =     "We describe the design and implementation of the
                 Glue-Nail deductive database system. Nail is a purely
                 declarative query language; Glue is a procedural
                 language used for non-query activities. The two
                 languages combined are sufficient to write a complete
                 application. Nail and Glue code are both compiled into
                 the target language IGlue. The Nail compiler uses
                 variants of the magic sets algorithm and supports
                 well-founded models. The Glue compiler's static
                 optimizer uses peephole techniques and data flow
                 analysis to improve code. The IGlue interpreter
                 features a run-time adaptive optimizer that reoptimizes
                 queries and automatically selects indexes. We also
                 describe the Glue-Nail benchmark suite, a set of
                 applications developed to evaluate the Glue-Nail
                 language and to measure the performance of the
                 system.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "language; performance; query optimization",
}

@Article{Ramakrishnan:1994:CDS,
  author =       "Raghu Ramakrishnan and Divesh Srivastava and S.
                 Sudarshan and Praveen Seshadri",
  title =        "The {CORAL} Deductive System",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "2",
  pages =        "161--210",
  month =        apr,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:29 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ramakrishnan:Raghu.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Seshadri:Praveen.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Srivastava:Divesh.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sudarshan:S=.html",
  abstract =     "CORAL is a deductive system that supports a rich
                 declarative language, and an interface to C++, which
                 allows for a combination of declarative and imperative
                 programming. A CORAL declarative program can be
                 organized as a collection of interacting modules. CORAL
                 supports a wide range of evaluation strategies, and
                 automatically chooses an efficient strategy for each
                 module in the program. Users can guide query
                 optimization by selecting from a wide range of control
                 choices. The CORAL system provides imperative
                 constructs to update, insert, and delete facts. Users
                 can program in a combination of declarative CORAL and
                 C++ extended with CORAL primitives. A high degree of
                 extensibility is provided by allowing C++ programmers
                 to use the class structure of C++ to enhance the CORAL
                 implementation. CORAL provides support for main-memory
                 data and, using the EXODUS storage manager,
                 disk-resident data. We present a comprehensive view of
                 the system from broad design goals, the language, and
                 the architecture, to language interfaces and
                 implementation details.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "deductive database; logic programming system; query
                 language",
}

@Article{Kiessling:1994:DSE,
  author =       "Werner Kie{\ss}ling and Helmut Schmidt and Werner
                 Strau{\ss} and Gerhard D{\"u}nzinger",
  title =        "{DECLARE} and {SDS}: Early Efforts to Commercialize
                 Deductive Database Technology",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "2",
  pages =        "211--243",
  month =        apr,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:29 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/D=uuml=nzinger:Gerhard.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kie=szlig=ling:Werner.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Schmidt:Helmut.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Strau=szlig=:Werner.html",
  abstract =     "The Smart Data System (SDS) and its declarative query
                 language, Declarative Reasoning, represent the first
                 large-scale effort to commercialize deductive database
                 technology. SDS offers the functionality of deductive
                 reasoning in a distributed, heterogeneous database
                 environment. In this article we discuss several
                 interesting aspects of the query compilation and
                 optimization process. The emphasis is on the query
                 execution plan data structure and its transformations
                 by the optimizing rule compiler. Through detailed case
                 studies we demonstrate that efficient and very compact
                 runtime code can be generated. We also discuss our
                 experiences gained from a large pilot application (the
                 MVV-expert) and report on several issues of practical
                 interest in engineering such a complex system,
                 including the migration from Lisp to C. We argue that
                 heuristic knowledge and control should be made an
                 integral part of deductive databases.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "declarative reasoning; distributed query processing;
                 heuristic control; multi-databases; productization;
                 query optimizer",
}

@Article{Vaghani:1994:ADD,
  author =       "Jayen Vaghani and Kotagiri Ramamohanarao and David B.
                 Kemp and Zoltan Somogyi and Peter J. Stuckey and Tim
                 S. Leask and James Harland",
  title =        "The {Aditi} Deductive Database System",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "2",
  pages =        "245--288",
  month =        apr,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:29 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Harland:James.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kemp:David_B=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Leask:Tim_S=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ramamohanarao:Kotagiri.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Somogyi:Zoltan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Stuckey:Peter_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/v/Vaghani:Jayen.html",
  abstract =     "Deductive databases generalize relational databases by
                 providing support for recursive views and non-atomic
                 data. Aditi is a deductive system based on the
                 client-server model; it is inherently multi-user and
                 capable of exploiting parallelism on shared-memory
                 multiprocessors. The back-end uses relational
                 technology for efficiency in the management of
                 disk-based data and uses optimization algorithms
                 especially developed for the bottom-up evaluation of
                 logical queries involving recursion. The front-end
                 interacts with the user in a logical language that has
                 more expressive power than relational query languages.
                 We present the structure of Aditi, discuss its
                 components in some detail, and present performance
                 figures.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "implementation; logic; multi-user; parallelism;
                 relational database",
}

@Article{Anonymous:1994:SIP,
  author =       "Anonymous",
  title =        "Special issue on prototypes of deductive database
                 systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "2",
  pages =        "??--??",
  month =        apr,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:29 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Lee:1994:EIV,
  author =       "Byung Suk Lee and Gio Wiederhold",
  title =        "Efficiently Instantiating View-Objects From Remote
                 Relational Databases",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "3",
  pages =        "289--323",
  month =        jul,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:30 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lee:Byung_Suk.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Wiederhold:Gio.html",
  abstract =     "View-objects are complex objects that are instantiated
                 by delivering a query to a database and converting the
                 query result into a nested structure. In relational
                 databases, query results are conventionally retrieved
                 as a single flat relation, which contains duplicate
                 subtuples in its composite tuples. These duplicate
                 subtuples increase the amount of data to be handled and
                 thus degrade performance. In this article, we describe
                 two new methods that retrieve a query result in
                 structures other than a single flat relation. One
                 method retrieves a set of relation fragments, and the
                 other retrieves a single-nested relation. We first
                 describe their algorithms and cost models, and then
                 present the cost comparison results in a client-server
                 architecture with a relational main memory database
                 residing on a server.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "client server; complex object; nested relation; query
                 optimization; relation fragments",
}

@Article{Barbara-Milla:1994:DPT,
  author =       "Daniel Barbar{\'a}-Mill{\'a} and Hector
                 Garcia-Molina",
  title =        "The demarcation protocol: a technique for maintaining
                 constraints in distributed database systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "3",
  pages =        "325--353",
  month =        jul,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:30 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Traditional protocols for distributed database
                 management have a high message overhead; restrain or
                 lock access to resources during protocol execution; and
                 may become impractical for some scenarios like
                 real-time systems and very large distributed databases.
                 In this article, we present the demarcation protocol;
                 it overcomes these problems by using explicit
                 consistency constraints as the correctness criteria.
                 The method establishes safe limits as `lines drawn in
                 the sand' for updates, and makes it possible to change
                 these limits dynamically, enforcing the constraints at
                 all times. We show how this technique can be applied to
                 linear arithmetic, existential, key, and approximate
                 copy constraints.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "consistency constraints; serializability; transaction
                 limits",
}

@Article{Barbara:1994:DPT,
  author =       "Daniel Barbar{\'a} and Hector Garcia-Molina",
  title =        "The Demarcation Protocol: {A} Technique for
                 Maintaining Constraints in Distributed Database
                 Systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "3",
  pages =        "325--353",
  month =        jul,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:01 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Barbar=aacute=:Daniel.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Garcia=Molina:Hector.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Bertino:1994:ICO,
  author =       "Elisa Bertino",
  title =        "Index Configuration in Object-Oriented Databases",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "3",
  pages =        "355--399",
  month =        jul,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:30 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Bertino:Elisa.html",
  abstract =     "In relational databases, an attribute of a relation
                 can have only a single primitive value, making it
                 cumbersome to model complex objects. The
                 object-oriented paradigm removes this difficulty by
                 introducing the notion of nested objects, which allows
                 the value of an object attribute to be another object
                 or a set of other objects. This means that a class
                 consists of a set of attributes, and the values of the
                 attributes are objects that belong to other classes;
                 that is, the definition of a class forms a hierarchy of
                 classes. All attributes of the nested classes are
                 nested attributes of the root of the hierarchy. A
                 branch of such hierarchy is called a {\em path}. In
                 this article, we address the problem of index
                 configuration for a given path. We first summarize some
                 basic concepts, and introduce the concept of index
                 configuration for a path. Then we present cost formulas
                 to evaluate the costs of the various configurations.
                 Finally, we present the algorithm that determines the
                 optimal configuration, and show its correctness.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "index selection; physical database design; query
                 optimization",
}

@Article{Guting:1994:ISD,
  author =       "Ralf Hartmut G{\"u}ting",
  title =        "An introduction to spatial database systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "4",
  pages =        "357--399",
  month =        oct,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:31 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "We propose a definition of a spatial database system
                 as a database system that offers spatial data types in
                 its data model and query language, and supports spatial
                 data types in its implementation, providing at least
                 spatial indexing and spatial join methods. Spatial
                 database systems offer the underlying database
                 technology for geographic information systems and other
                 applications. We survey data modeling, querying, data
                 structures and algorithms, and system architecture for
                 such systems. The emphasis is on describing known
                 technology in a coherent manner, rather than listing
                 open problems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Guting:1994:SIS,
  author =       "Ralf Hartmut G{\"u}ting",
  title =        "Special Issue on Spatial Database Systems: An
                 Introduction to Spatial Database Systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "4",
  pages =        "357--399",
  month =        oct,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:01 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/G=uuml=ting:Ralf_Hartmut.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Baumann:1994:MMD,
  author =       "Peter Baumann",
  title =        "Management of Multidimensional Discrete Data",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "4",
  pages =        "401--444",
  month =        oct,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:31 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Baumann:Peter.html",
  abstract =     "Spatial database management involves two main
                 categories of data: vector and raster data. The former
                 has received a lot of in-depth investigation; the
                 latter still lacks a sound framework. Current DBMSs
                 either regard raster data as pure byte sequences where
                 the DBMS has no knowledge about the underlying
                 semantics, or they do not complement array structures
                 with storage mechanisms suitable for huge arrays, or
                 they are designed as specialized systems with
                 sophisticated imaging functionality, but no general
                 database capabilities (e.g., a query language). Many
                 types of array data will require database support in
                 the future, notably 2-D images, audio data and general
                 signal-time series (1-D), animations (3-D), static or
                 time-variant voxel fields (3-D and 4-D), and the
                 ISO/IEC PIKS (Programmer's Imaging Kernel System)
                 BasicImage type (5-D). In this article, we propose a
                 comprehensive support of {\em multidimensional discrete
                 data\/} (MDD) in databases, including operations on
                 arrays of arbitrary size over arbitrary data types. A
                 set of requirements is developed, a small set of
                 language constructs is proposed (based on a formal
                 algebraic semantics), and a novel MDD architecture is
                 outlined to provide the basis for efficient MDD query
                 evaluation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "image database systems; multimedia database systems;
                 spatial index; tiling",
}

@Article{Chu:1994:SMA,
  author =       "Wesley W. Chu and Ion Tim Ieong and Ricky K. Taira",
  title =        "A Semantic Modeling Approach for Image Retrieval by
                 Content",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "4",
  pages =        "445--477",
  month =        oct,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:31 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chu:Wesley_W=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/i/Ieong:Ion_Tim.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Taira:Ricky_K=.html",
  abstract =     "We introduce a semantic data model to capture the
                 hierarchical, spatial, temporal, and evolutionary
                 semantics of images in pictorial databases. This model
                 mimics the user's conceptual view of the image content,
                 providing the framework and guidelines for
                 preprocessing to extract image features. Based on the
                 model constructs, a spatial evolutionary query language
                 (SEQL), which provides direct image object manipulation
                 capabilities, is presented. With semantic information
                 captured in the model, spatial evolutionary queries are
                 answered efficiently. Using an object-oriented
                 platform, a prototype medical-image management system
                 was implemented at UCLA to demonstrate the feasibility
                 of the proposed approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "image; medical; multimedia databases; spatial query
                 processing; temporal evolutionary query processing",
}

@Article{Papadias:1994:QRS,
  author =       "Dimitris Papadias and Timos K. Sellis",
  title =        "Qualitative Representation of Spatial Knowledge in
                 Two-Dimensional Space",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "4",
  pages =        "479--516",
  month =        oct,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:31 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Papadias:Dimitris.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sellis:Timos_K=.html",
  abstract =     "Various relation-based systems, concerned with the
                 qualitative representation and processing of spatial
                 knowledge, have been developed in numerous application
                 domains. In this article, we identify the common
                 concepts underlying qualitative spatial knowledge
                 representation, we compare the representational
                 properties of the different systems, and we outline the
                 computational tasks involved in relation-based spatial
                 information processing. We also describe {\em symbolic
                 spatial indexes}, relation-based structures that
                 combine several ideas in spatial knowledge
                 representation. A symbolic spatial index is an array
                 that preserves only a set of spatial relations among
                 distinct objects in an image, called the modeling
                 space; the index array discards information, such as
                 shape and size of objects, and irrelevant spatial
                 relations. The construction of a symbolic spatial index
                 from an input image can be thought of as a
                 transformation that keeps only a set of representative
                 points needed to define the relations of the modeling
                 space. By keeping the relative arrangements of the
                 representative points in symbolic spatial indexes and
                 discarding all other points, we maintain enough
                 information to answer queries regarding the spatial
                 relations of the modeling space without the need to
                 access the initial image or an object database.
                 Symbolic spatial indexes can be used to solve problems
                 involving route planning, composition of spatial
                 relations, and update operations.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "qualitative spatial information processing;
                 representation of direction and topological relations;
                 spatial data models; spatial query languages",
}

@Article{Lin:1994:TTI,
  author =       "King Ip Lin and H. V. Jagadish and Christos
                 Faloutsos",
  title =        "The {TV}-Tree: An Index Structure for High-Dimensional
                 Data",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "4",
  pages =        "517--542",
  month =        oct,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:31 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb3.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Faloutsos:Christos.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/j/Jagadish:H=_V=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lin:King=Ip.html",
  abstract =     "We propose a file structure to index
                 high-dimensionality data, which are typically points in
                 some feature space. The idea is to use only a few of
                 the features, using additional features only when the
                 additional discriminatory power is absolutely
                 necessary. We present in detail the design of our tree
                 structure and the associated algorithms that handle
                 such `varying length' feature vectors. Finally, we
                 report simulation results, comparing the proposed
                 structure with the $R*$-tree, which is one of the most
                 successful methods for low-dimensionality spaces. The
                 results illustrate the superiority of our method, which
                 saves up to 80\% in disk accesses.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "query by content; similarity retrieval; spatial
                 index",
}

@Article{Anonymous:1994:SIS,
  author =       "Anonymous",
  title =        "Special issue on spatial database systems",
  journal =      j-VLDB-J,
  volume =       "3",
  number =       "4",
  pages =        "??--??",
  month =        oct,
  year =         "1994",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:31 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Constantopoulos:1995:SIB,
  author =       "Panos Constantopoulos and Matthias Jarke and John
                 Mylopoulos and Yannis Vassiliou",
  title =        "The Software Information Base: {A} Server for Reuse",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "1",
  pages =        "1--43",
  month =        jan,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:32 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Constantopoulos:Panos.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/j/Jarke:Matthias.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mylopoulos:John.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/v/Vassiliou:Yannis.html",
  abstract =     "We present an experimental software repository system
                 that provides organization, storage, management, and
                 access facilities for reusable software components. The
                 system, intended as part of an applications development
                 environment, supports the representation of information
                 about requirements, designs and implementations of
                 software, and offers facilities for visual presentation
                 of the software objects. This article details the
                 features and architecture of the repository system, the
                 technical challenges and the choices made for the
                 system development along with a usage scenario that
                 illustrates its functionality. The system has been
                 developed and evaluated within the context of the
                 ITHACA project, a technology integration/software
                 engineering project sponsored by the European
                 Communities through the ESPRIT program, aimed at
                 developing an integrated reuse-centered application
                 development and support environment based on
                 object-oriented techniques.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "conceptual modeling; information storage and
                 retrieval; object-oriented databases; reuse; software
                 engineering",
}

@Article{Clifton:1995:HDQ,
  author =       "Chris Clifton and Hector Garcia-Molina and David
                 Bloom",
  title =        "{HyperFile}: {A} Data and Query Model for Documents",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "1",
  pages =        "45--86",
  month =        jan,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:32 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Bloom:David.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Clifton:Chris.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Garcia=Molina:Hector.html",
  abstract =     "Non-quantitative information such as documents and
                 pictures pose interesting new problems in the database
                 world. Traditional data models and query languages do
                 not provide appropriate support for this information.
                 Such data are typically stored in file systems, which
                 do not provide the security, integrity, or query
                 features of database management systems. The hypertext
                 model has emerged as a good interface to this
                 information; however, {\em finding\/} information using
                 hypertext browsing does not scale well. We developed a
                 query interface that serves as an extension of the
                 browsing model of hypertext systems. These queries
                 minimize the repeated user interactions required to
                 locate data in a standard hypertext system. HyperFile
                 is a prototype data server interface. In this article,
                 we describe HyperFile, including a number of issues
                 such as query generation, query processing, and
                 indexing.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "hypertext; indexing; user interface",
}

@Article{Agrawal:1995:OSL,
  author =       "Divyakant Agrawal and Amr {El Abbadi} and Richard
                 Jeffers and Lijing Lin",
  title =        "Ordered Shared Locks for Real-Time Databases",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "1",
  pages =        "87--126",
  month =        jan,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:32 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Abbadi:Amr_El.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Agrawal:Divyakant.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/j/Jeffers:Richard.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lin:Lijing.html",
  abstract =     "We propose locking protocols for real-time databases.
                 Our approach has two main motivations: First, locking
                 protocols are widely accepted and used in most database
                 systems. Second, in real-time databases it has been
                 shown that the blocking behavior of transactions in
                 locking protocols results in performance degradation.
                 We use a new relationship between locks called ordered
                 sharing to eliminate blocking that arises in the
                 traditional locking protocols. Ordered sharing
                 eliminates blocking of read and write operations but
                 may result in delayed termination. Since timeliness and
                 not response time is the crucial factor in real-time
                 databases, our protocols exploit this delay to allow
                 transactions to execute within the slacks of delayed
                 transactions. We compare the performance of the
                 proposed protocols with the two-phase locking protocol
                 for real-time databases. Our experiments indicate that
                 the proposed protocols significantly reduce the
                 percentage of missed deadlines in the system for a
                 variety of workloads.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; time-critical scheduling;
                 transaction management",
}

@Article{Dan:1995:CDA,
  author =       "Asit Dan and Philip S. Yu and Jen Yao Chung",
  title =        "Characterization of Database Access Pattern for
                 Analytic Prediction of Buffer Hit Probability",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "1",
  pages =        "127--154",
  month =        jan,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:32 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chung:Jen=Yao.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Dan:Asit.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Yu:Philip_S=.html",
  abstract =     "The analytic prediction of buffer hit probability,
                 based on the characterization of database accesses from
                 real reference traces, is extremely useful for workload
                 management and system capacity planning. The knowledge
                 can be helpful for proper allocation of buffer space to
                 various database relations, as well as for the
                 management of buffer space for a mixed transaction and
                 query environment. Access characterization can also be
                 used to predict the buffer invalidation effect in a
                 multi-node environment which, in turn, can influence
                 transaction routing strategies. However, it is a
                 challenge to characterize the database access pattern
                 of a real workload reference trace in a simple manner
                 that can easily be used to compute buffer hit
                 probability. In this article, we use a characterization
                 method that distinguishes three types of access
                 patterns from a trace: (1) locality within a
                 transaction, (2) random accesses by transactions, and
                 (3) sequential accesses by long queries. We then
                 propose a concise way to characterize the access skew
                 across randomly accessed pages by logically grouping
                 the large number of data pages into a small number of
                 partitions such that the frequency of accessing each
                 page within a partition can be treated as equal. Based
                 on this approach, we present a recursive binary
                 partitioning algorithm that can infer the access skew
                 characterization from the buffer hit probabilities for
                 a subset of the buffer sizes. We validate the buffer
                 hit predictions for single and multiple node systems
                 using production database traces. We further show that
                 the proposed approach can predict the buffer hit
                 probability of a composite workload from those of its
                 component files.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access skew; analytic prediction; database access
                 characterization; reference trace; sequential access;
                 workload management",
}

@Article{Peckham:1995:DME,
  author =       "Joan Peckham and Bonnie MacKellar and Michael
                 Doherty",
  title =        "Data Model for Extensible Support of Explicit
                 Relationships in Design Databases",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "2",
  pages =        "157--191",
  month =        apr,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:33 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Doherty:Michael.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/MacKellar:Bonnie.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Peckham:Joan.html",
  abstract =     "We describe the conceptual model of SORAC, a data
                 modeling system developed at the University of Rhode
                 Island. SORAC supports both semantic objects and
                 relationships, and provides a tool for modeling
                 databases needed for complex design domains. SORAC's
                 set of built-in semantic relationships permits the
                 schema designer to specify enforcement rules that
                 maintain constraints on the object and relationship
                 types. SORAC then automatically generates C++ code to
                 maintain the specified enforcement rules, producing a
                 schema that is compatible with Ontos. This facilitates
                 the task of the schema designer, who no longer has to
                 ensure that all methods on object classes correctly
                 maintain necessary constraints. In addition, explicit
                 specification of enforcement rules permits automated
                 analysis of enforcement propagations. We compare the
                 interpretations of relationships within the semantic
                 and object-oriented models as an introduction to the
                 mixed model that SORAC supports. Next, the set of
                 built-in SORAC relationship types is presented in terms
                 of the enforcement rules permitted on each relationship
                 type. We then use the modeling requirements of an
                 architectural design support system, called
                 ArchObjects, to demonstrate the capabilities of SORAC.
                 The implementation of the current SORAC prototype is
                 also briefly discussed.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "computer-aided architectural design; database
                 constraints; relationship semantics; semantic and
                 object-oriented data modeling",
  xxpages =      "157--192",
}

@Article{Teniente:1995:UKB,
  author =       "Ernest Teniente and Antoni Oliv{\'e}",
  title =        "Updating Knowledge Bases While Maintaining Their
                 Consistency",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "2",
  pages =        "193--241",
  month =        apr,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:33 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/o/Oliv=eacute=:Antoni.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Teniente:Ernest.html",
  abstract =     "When updating a knowledge base, several problems may
                 arise. One of the most important problems is that of
                 integrity constraints satisfaction. The classic
                 approach to this problem has been to develop methods
                 for {\em checking\/} whether a given update violates an
                 integrity constraint. An alternative approach consists
                 of trying to repair integrity constraints violations by
                 performing additional updates that {\em maintain\/}
                 knowledge base consistency. Another major problem in
                 knowledge base updating is that of {\em view updating},
                 which determines how an update request should be
                 translated into an update of the underlying base facts.
                 We propose a new method for updating knowledge bases
                 while maintaining their consistency. Our method can be
                 used for both integrity constraints maintenance and
                 view updating. It can also be combined with any
                 integrity checking method for view updating and
                 integrity checking. The kind of updates handled by our
                 method are: updates of base facts, view updates,
                 updates of deductive rules, and updates of integrity
                 constraints. Our method is based on events and
                 transition rules, which explicitly define the
                 insertions and deletions induced by a knowledge base
                 update. Using these rules, an extension of the SLDNF
                 procedure allows us to obtain all possible minimal ways
                 of updating a knowledge base without violating any
                 integrity constraint.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "integrity checking; integrity maintenance; view
                 updating",
}

@Article{Guting:1995:RBS,
  author =       "Ralf Hartmut G{\"u}ting and Markus Schneider",
  title =        "Realm-Based Spatial Data Types: The {ROSE} Algebra",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "2",
  pages =        "243--286",
  month =        apr,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:33 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/G=uuml=ting:Ralf_Hartmut.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Schneider:Markus.html",
  abstract =     "Spatial data types or algebras for database systems
                 should (1) be fully general, that is, closed under set
                 operations, (2) have formally defined semantics, (3) be
                 defined in terms of finite representations available in
                 computers, (4) offer facilities to enforce geometric
                 consistency of related spatial objects, and (5) be
                 independent of a particular DBMS data model, but
                 cooperate with any. We present an algebra that uses
                 {\em realms\/} as geometric domains underlying spatial
                 data types. A realm, as a general database concept, is
                 a finite, dynamic, user-defined structure underlying
                 one or more system data types. Problems of numerical
                 robustness and topological correctness are solved
                 within and below the realm layer so that spatial
                 algebras defined above a realm have very nice algebraic
                 properties. Realms also interact with a DMBS to enforce
                 geometric consistency on object creation or update. The
                 ROSE algebra is defined on top of realms and offers
                 general types to represent point, line, and region
                 features, together with a comprehensive set of
                 operations. It is described within a polymorphic type
                 system and interacts with a DMBS data model and query
                 language through an abstract {\em object model
                 interface.} An example integration of ROSE into the
                 object-oriented data model $O^2$ and its query language
                 is presented.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "finite resolution; geometric consistency; numerical
                 robustness; object model interface; realm; topological
                 correctness",
}

@Article{Templeton:1995:IDC,
  author =       "Marjorie Templeton and Herbert Henley and Edward Maros
                 and Darrel J. Van Buer",
  title =        "{InterViso}: Dealing With the Complexity of Federated
                 Database Access",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "2",
  pages =        "287--317",
  month =        apr,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:33 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Buer:Darrel_J=_Van.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Henley:Herbert.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Maros:Edward.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Templeton:Marjorie.html",
  abstract =     "Connectivity products are finally available to provide
                 the `highways' between computers containing data. IBM
                 has provided strong validation of the concept with
                 their `Information Warehouse.' DBMS vendors are
                 providing gateways into their products, and SQL is
                 being retrofitted on many older DBMSs to make it easier
                 to access data from standard 4GL products and
                 application development systems. The next step needed
                 for data integration is to provide (1) a common data
                 dictionary with a conceptual schema across the data to
                 mask the many differences that occur when databases are
                 developed independently and (2) a server that can
                 access and integrate the databases using information
                 from the data dictionary. In this article, we discuss
                 InterViso, one of the first commercial federated
                 database products. InterViso is based on Mermaid, which
                 was developed at SDC and Unisys (Templeton et al.,
                 1987b). It provides a value added layer above
                 connectivity products to handle views across databases,
                 schema translation, and transaction management.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data warehouse; database integration; federated
                 database",
  xxpages =      "287--318",
}

@Article{Atkinson:1995:SIP,
  author =       "Malcolm P. Atkinson and Ronald Morrison",
  title =        "Special Issue on Persistent Object Systems:
                 Orthogonally Persistent Object Systems",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "3",
  pages =        "319--401",
  month =        jul,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:01 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Atkinson:Malcolm_P=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Morrison:Ronald.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Atkinson:1995:OPO,
  author =       "Malcolm Atkinson and Ronald Morrison",
  title =        "Orthogonally persistent object systems",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "3",
  pages =        "319--402",
  month =        jul,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:34 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Persistent Application Systems (PASs) are of
                 increasing social and economic importance. They have
                 the potential to be long-lived, concurrently accessed,
                 and consist of large bodies of data and programs.
                 Typical examples of PASs are CAD/CAM systems, office
                 automation, CASE tools, software engineering
                 environments, and patient-care support systems in
                 hospitals. Orthogonally persistent object systems are
                 intended to provide improved support for the design,
                 construction, maintenance, and operation of PASs.
                 Persistence abstraction allows the creation and
                 manipulation of data in a manner that is independent of
                 its lifetime, thereby integrating the database view of
                 information with the programming language view. This
                 yields a number of advantages in terms of orthogonal
                 design and programmer productivity which are beneficial
                 for PASs. Design principles have been proposed for
                 persistent systems. By following these principles,
                 languages that provide persistence as a basic
                 abstraction have been developed. In this paper, the
                 motivation for orthogonal persistence is reviewed along
                 with the above mentioned design principles. The
                 concepts for integrating programming languages and
                 databases through the persistence abstraction, and
                 their benefits, are given. The technology to support
                 persistence, the achievements, and future directions of
                 persistence research are then discussed.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database programming languages; orthogonal
                 persistence; persistent application systems; persistent
                 programming languages",
}

@Article{Albano:1995:FPL,
  author =       "Antonio Albano and Giorgio Ghelli and Renzo Orsini",
  title =        "{Fibonacci}: {A} Programming Language for Object
                 Databases",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "3",
  pages =        "403--444",
  month =        jul,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:34 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Albano:Antonio.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Ghelli:Giorgio.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/o/Orsini:Renzo.html",
  abstract =     "Fibonacci is an object-oriented database programming
                 language characterized by static and strong typing, and
                 by new mechanisms for modeling databases in terms of
                 objects with roles, classes, and associations. A brief
                 introduction to the language is provided to present
                 those features, which are particularly suited to
                 modeling complex databases. Examples of the use of
                 Fibonacci are given with reference to the prototype
                 implementation of the language.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data models; database programming languages; objects
                 with roles",
}

@Article{Ozsu:1995:TUB,
  author =       "M. Tamer {\"O}zsu and Randal J. Peters and Duane
                 Szafron and Boman Irani and Anna Lipka and Adriana
                 Mu{\~n}oz",
  title =        "{TIGUKAT}: {A} Uniform Behavioral Objectbase
                 Management System",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "3",
  pages =        "445--492",
  month =        jul,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:34 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/=/=Ouml=zsu:M=_Tamer.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/i/Irani:Boman.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lipka:Anna.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mu=ntilde=oz:Adriana.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Peters:Randal_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Szafron:Duane.html",
  abstract =     "We describe the TIGUKAT objectbase management system,
                 which is under development at the Laboratory for
                 Database Systems Research at the University of Alberta.
                 TIGUKAT has a novel object model, whose identifying
                 characteristics include a purely behavioral semantics
                 and a uniform approach to objects. Everything in the
                 system, including types, classes, collections,
                 behaviors, and functions, as well as meta-information,
                 is a first-class object with well-defined behavior. In
                 this way, the model abstracts everything, including
                 traditional structural notions such as instance
                 variables, method implementation, and schema
                 definition, into a uniform semantics of behaviors on
                 objects. Our emphasis in this article is on the object
                 model, its implementation, the persistence model, and
                 the query language. We also (briefly) present other
                 database management functions that are under
                 development such as the query optimizer, the version
                 control system, and the transaction manager.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database management; objectbase management; persistent
                 storage system; reflective system",
}

@Article{Benzaken:1995:TDP,
  author =       "V{\'e}ronique Benzaken and Anne Doucet",
  title =        "{Th{\'e}mis}: {A} Database Programming Language
                 Handling Integrity Constraints",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "3",
  pages =        "493--517",
  month =        jul,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:34 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Benzaken:V=eacute=ronique.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Doucet:Anne.html",
  abstract =     "This article presents a database programming language,
                 Th{\'e}mis, which supports subtyping and class
                 hierarchies, and allows for the definition of integrity
                 constraints in a global and declarative way. We first
                 describe the salient features of the language: types,
                 names, classes, integrity constraints (including
                 methods), and transactions. The inclusion of methods
                 into integrity constraints allows an increase of the
                 declarative power of these constraints. Indeed, the
                 information needed to define a constraint is not always
                 stored in the database through attributes, but is
                 sometimes computed or derived data. Then, we address
                 the problem of efficiently checking constraints. More
                 specifically, we consider two different problems: (1)
                 statically reducing the number of constraints to be
                 checked, and (2) generating an efficient run-time
                 checker. Using simple strategies, one can significantly
                 improve the efficiency of the verification. We show how
                 to reduce the number of constraints to be checked by
                 characterizing the portions of the database that are
                 involved in both the constraints and in a transaction.
                 We also show how to generate efficient algorithms for
                 checking a large class of constraints. We show how all
                 the techniques presented exploit the underlying type
                 system, which provides significant help in solving (1)
                 and \1. Last, the current status of the Th{\'e}mis
                 prototype is presented.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database programming language; integrity constraints;
                 program analysis",
}

@Article{Kemper:1995:APS,
  author =       "Alfons Kemper and Donald Kossmann",
  title =        "Adaptable Pointer Swizzling Strategies in Object
                 Bases: Design, Realization, and Quantitative Analysis",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "3",
  pages =        "519--566",
  month =        jul,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:34 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kemper:Alfons.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kossmann:Donald.html",
  abstract =     "In this article, different techniques for {\em
                 `pointer swizzling'\/} are classified and evaluated for
                 optimizing the access to main-memory resident
                 persistent objects. To speed up the access along
                 inter-object references, the persistent pointers in the
                 form of unique object identifiers (OIDs) are
                 transformed (swizzled) into main-memory pointers
                 (addresses). Pointer swizzling techniques can be
                 divided into two classes: (1) those that allow
                 replacement of swizzled objects from the buffer before
                 the end of an application program, and (2) those that
                 rule out the displacement of swizzled objects. The
                 first class (i.e., techniques that take `precautions'
                 for the replacement of swizzled objects) has not yet
                 been thoroughly investigated. Four different pointer
                 swizzling techniques allowing object replacement are
                 investigated and compared with the performance of an
                 object manager employing no pointer swizzling. The
                 extensive qualitative and quantitative
                 evaluation---only part of which could be presented in
                 this article---demonstrate that there is no {\em one\/}
                 superior pointer swizzling strategy for {\em all\/}
                 application profiles. Therefore, an adaptable object
                 base run-time system is devised that employs the full
                 range of pointer swizzling strategies, depending on the
                 application profile characteristics that are determined
                 by, for example, monitoring in combination with
                 sampling, user specifications, and/or program
                 analysis.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "object-oriented database systems; performance
                 evaluation; pointer swizzling",
  xxpages =      "519--567",
}

@Article{Anonymous:1995:SIP,
  author =       "Anonymous",
  title =        "Special issue on persistent object systems",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "3",
  pages =        "??--??",
  month =        jul,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:34 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Barbara:1995:SSO,
  author =       "Daniel Barbar{\'a} and Tomasz Imielinski",
  title =        "Special System-oriented Section: The Best of {SIGMOD}
                 1994: Sleepers and Workaholics: Caching Strategies in
                 Mobile Environments",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "567--602",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:01 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Barbar=aacute=:Daniel.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/i/Imielinski:Tomasz.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Barbara:1995:SWC,
  author =       "Daniel Barbar{\'a} and Tomasz Imieli{\'n}ski",
  title =        "Sleepers and workaholics: caching strategies in mobile
                 environments (extended version)",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "567--602",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:35 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In the mobile wireless computing environment of the
                 future, a large number of users, equipped with
                 low-powered palmtop machines, will query databases over
                 wireless communication channels. Palmtop-based units
                 will often be disconnected for prolonged periods of
                 time, due to battery power saving measures; palmtops
                 also will frequently relocate between different cells,
                 and will connect to different data servers at different
                 times. Caching of frequently accessed data items will
                 be an important technique that will reduce contention
                 on the narrow-bandwidth, wireless channel. However,
                 cache individualization strategies will be severely
                 affected by the disconnection and mobility of the
                 clients. The server may no longer know which clients
                 are currently residing under its cell, and which of
                 them are currently on. We propose a taxonomy of
                 different cache invalidation strategies, and study the
                 impact of clients' disconnection times on their
                 performance. We study ways to improve further the
                 efficiency of the invalidation techniques described. We
                 also describe how our techniques can be implemented
                 over different network environments.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "caching; data management; information services;
                 wireless",
}

@Article{Nyberg:1995:ACS,
  author =       "Chris Nyberg and Tom Barclay and Zarka Cvetanovic and
                 Jim Gray and David B. Lomet",
  title =        "{AlphaSort}: {A} Cache-Sensitive Parallel External
                 Sort",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "603--627",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:35 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Barclay:Tom.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Cvetanovic:Zarka.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Gray:Jim.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lomet:David_B=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Nyberg:Chris.html",
  abstract =     "A new sort algorithm, called AlphaSort, demonstrates
                 that commodity processors and disks can handle
                 commercial batch workloads. Using commodity processors,
                 memory, and arrays of SCSI disks, AlphaSort runs the
                 industry-standard sort benchmark in seven seconds. This
                 beats the best published record on a 32-CPU 32-disk
                 Hypercube by 8:1. On another benchmark, AlphaSort
                 sorted more than a gigabyte in one minute. AlphaSort is
                 a cache-sensitive, memory-intensive sort algorithm. We
                 argue that modern architectures require algorithm
                 designers to re-examine their use of the memory
                 hierarchy. AlphaSort uses clustered data structures to
                 get good cache locality, file striping to get high disk
                 bandwidth, QuickSort to generate runs, and
                 replacement-selection to merge the runs. It uses shared
                 memory multiprocessors to break the sort into subsort
                 chores. Because startup times are becoming a
                 significant part of the total time, we propose two new
                 benchmarks: (1) MinuteSort: how much can you sort in
                 one minute, and (2) PennySort: how much can you sort
                 for one penny.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "Alpha; cache; DEC 7000; disk; memory; parallel; sort;
                 striping",
  xxpages =      "603--628",
}

@Article{White:1995:QHP,
  author =       "Seth J. White and David J. DeWitt",
  title =        "{QuickStore}: {A} High Performance Mapped Object
                 Store",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "629--673",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:35 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/DeWitt:David_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/White:Seth_J=.html",
  abstract =     "QuickStore is a memory-mapped storage system for
                 persistent C++, built on top of the EXODUS Storage
                 Manager. QuickStore provides fast access to in-memory
                 objects by allowing application programs to access
                 objects via normal virtual memory pointers. This
                 article presents the results of a detailed performance
                 study using the OO7 benchmark. The study compares the
                 performance of QuickStore with the latest
                 implementation of the E programming language. The
                 QuickStore and E systems exemplify the two basic
                 approaches (hardware and software) that have been used
                 to implement persistence in object-oriented database
                 systems. In addition, both systems use the same
                 underlying storage manager and compiler, allowing us to
                 make a truly apples-to-apples comparison of the
                 hardware and software techniques.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "benchmark; client-server; memory-mapped;
                 object-oriented; performance; pointer swizzling",
}

@Article{Swami:1995:EPF,
  author =       "Arun N. Swami and K. Bernhard Schiefer",
  title =        "Estimating Page Fetches for Index Scans with Finite
                 {LRU} Buffers",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "675--701",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:35 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Schiefer:K=_Bernhard.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Swami:Arun_N=.html",
  abstract =     "We describe an algorithm for estimating the number of
                 page fetches for a partial or complete scan of a B-tree
                 index. The algorithm obtains estimates for the number
                 of page fetches for an index scan when given the number
                 of tuples selected and the number of LRU buffers
                 currently available. The algorithm has an initial phase
                 that is performed exactly once before any estimates are
                 calculated. This initial phase, involving LRU buffer
                 modeling, requires a scan of all the index entries and
                 calculates the number of page fetches for different
                 buffer sizes. An approximate empirical model is
                 obtained from this data. Subsequently, an inexpensive
                 estimation procedure is called by the query optimizer
                 whenever it needs an estimate of the page fetches for
                 the index scan. This procedure utilizes the empirical
                 model obtained in the initial phase.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "estimation; index scan; LRU; query optimization",
}

@Article{Landau:1995:HQA,
  author =       "Gad M. Landau and Jeanette P. Schmidt and Vassilis J.
                 Tsotras",
  title =        "Historical queries along multiple lines of time
                 evolution",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "703--726",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:35 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Traditional approaches to addressing historical
                 queries assume a {\em single\/} line of time evolution;
                 that is, a system (database, relation) evolves over
                 time through a sequence of transactions. Each
                 transaction always applies to the unique, current state
                 of the system, resulting in a new current state. There
                 are, however, complex applications where the system's
                 state evolves into {\em multiple\/} lines of evolution.
                 In general, this creates a tree (hierarchy) of
                 evolution lines, where each tree node represents the
                 time evolution of a particular subsystem. Multiple
                 lines create novel historical queries, such as {\em
                 vertical\/} or {\em horizontal\/} historical queries.
                 The key characteristic of these problems is that
                 portions of the history are shared; answering
                 historical queries should not necessitate duplication
                 of shared histories as this could increase the storage
                 requirements dramatically. Both the vertical and
                 horizontal historical queries have two parts: a
                 `search' part, where the time of interest is located
                 together with the appropriate subsystem, and a
                 reconstruction part, where the subsystem's state is
                 reconstructed for that time. This article focuses on
                 the search part; several reconstruction methods,
                 designed for single evolution lines can be applied once
                 the appropriate time of interest is located. For both
                 the vertical and the horizontal historical queries, we
                 present algorithms that work without duplicating shared
                 histories. Combinations of the vertical and horizontal
                 queries are possible, and enable searching in both
                 dimensions of the tree of evolutions.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access methods; CAD databases; data-structures;
                 rollback databases",
}

@Article{Landau:1995:RJA,
  author =       "Gad M. Landau and Jeanette P. Schmidt and Vassilis J.
                 Tsotras",
  title =        "Regular Journal Articles: Historical Queries Along
                 Multiple Lines of Time Evolution",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "703--726",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:01 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Landau:Gad_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Schmidt:Jeanette_P=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tsotras:Vassilis_J=.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Abiteboul:1995:PLM,
  author =       "Serge Abiteboul and Catriel Beeri",
  title =        "The Power of Languages for the Manipulation of Complex
                 Values",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "727--794",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:35 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb4.html;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Abiteboul:Serge.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Beeri:Catriel.html",
  abstract =     "Various models and languages for describing and
                 manipulating hierarchically structured data have been
                 proposed. Algebraic, calculus-based, and
                 logic-programming oriented languages have all been
                 considered. This article presents a general model for
                 complex values (i.e., values with hierarchical
                 structures), and languages for it based on the three
                 paradigms. The algebraic language generalizes those
                 presented in the literature; it is shown to be related
                 to the functional style of programming advocated by
                 Backus (1978). The notion of domain independence (from
                 relational databases) is defined, and syntactic
                 restrictions (referred to as safety conditions) on
                 calculus queries are formulated to guarantee domain
                 independence. The main results are: The
                 domain-independent calculus, the safe calculus, the
                 algebra, and the logic-programming oriented language
                 have equivalent expressive power. In particular,
                 recursive queries, such as the transitive closure, can
                 be expressed in each of the languages. For this result,
                 the algebra needs the powerset operation. A more
                 restricted version of safety is presented, such that
                 the restricted safe calculus is equivalent to the
                 algebra without the powerset. The results are extended
                 to the case where arbitrary functions and predicates
                 are used in the languages.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "complex object; complex value; database; database
                 model; query language",
}

@Article{Anonymous:1995:SSO,
  author =       "Anonymous",
  title =        "Special system-oriented section: the best of {SIGMOD}
                 `94",
  journal =      j-VLDB-J,
  volume =       "4",
  number =       "4",
  pages =        "??--??",
  month =        oct,
  year =         "1995",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:35 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{DeWitt:1996:POT,
  author =       "David J. {De Witt} and Jeffrey F. Naughton and John C.
                 Shafer and Shivakumar Venkataraman",
  title =        "Parallelizing {OODBMS} traversals: a performance
                 evaluation",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "1",
  pages =        "3--18",
  month =        jan,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:36 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/DeWitt:David_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Naughton:Jeffrey_F=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Shafer:John_C=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/v/Venkataraman:Shivakumar.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005001/60050003.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050003.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050003.ps.gz",
  abstract =     "In this paper we describe the design and
                 implementation of {\em ParSets}, a means of exploiting
                 parallelism in the SHORE OODBMS. We used ParSets to
                 parallelize the graph traversal portion of the OO7
                 OODBMS benchmark, and present speedup and scaleup
                 results from parallel SHORE running these traversals on
                 a cluster of commodity workstations connected by a
                 standard Ethernet. For some OO7 traversals, SHORE
                 achieved excellent speedup and scaleup; for other OO7
                 traversals, only marginal speedup and scaleup occurred.
                 The characteristics of these traversals shed light on
                 when the ParSet approach to parallelism can and cannot
                 be applied to speed up an application.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "Object-oriented database management systems;
                 Parallelism; ParSets; SHORE",
}

@Article{Sivasankaran:1996:PAR,
  author =       "Rajendran M. Sivasankaran and John A. Stankovic and
                 Donald F. Towsley and Bhaskar Purimetla and Krithi
                 Ramamritham",
  title =        "Priority Assignment in Real-Time Active Databases",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "1",
  pages =        "19--34",
  month =        jan,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:36 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Purimetla:Bhaskar.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ramamritham:Krithi.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sivasankaran:Rajendran_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Stankovic:John_A=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Towsley:Donald_F=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005001/60050019.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050019.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050019.ps.gz",
  abstract =     "Active databases and real-time databases have been
                 important areas of research in the recent past. It has
                 been recognized that many benefits can be gained by
                 integrating real-time and active database technologies.
                 However, not much work has been done in the area of
                 transaction processing in real-time active databases.
                 This paper deals with an important aspect of
                 transaction processing in real-time active databases,
                 namely the problem of assigning priorities to
                 transactions. In these systems, time-constrained
                 transactions trigger other transactions during their
                 execution. We present three policies for assigning
                 priorities to parent, immediate and deferred
                 transactions executing on a multiprocessor system and
                 then evaluate the policies through simulation. The
                 policies use different amounts of semantic information
                 about transactions to assign the priorities. The
                 simulator has been validated against the results of
                 earlier published studies. We conducted experiments in
                 three settings: a task setting, a main memory database
                 setting and a disk-resident database setting. Our
                 results demonstrate that dynamically changing the
                 priorities of transactions, depending on their behavior
                 (triggering rules), yields a substantial improvement in
                 the number of triggering transactions that meet their
                 deadline in all three settings.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "Active databases; Coupling mode; Deadlines;
                 ECA-priority assignment; Real-time databases",
}

@Article{Keller:1996:PBC,
  author =       "Arthur M. Keller and Julie Basu",
  title =        "A Predicate-based Caching Scheme for Client-Server
                 Database Architectures",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "1",
  pages =        "35--47",
  month =        jan,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:36 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Basu:Julie.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Keller:Arthur_M=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005001/60050035.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050035.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050035.ps.gz",
  abstract =     "We propose a new client-side data-caching scheme for
                 relational databases with a central server and multiple
                 clients. Data are loaded into each client cache based
                 on queries executed on the central database at the
                 server. These queries are used to form predicates that
                 describe the cache contents. A subsequent query at the
                 client may be satisfied in its local cache if we can
                 determine that the query result is entirely contained
                 in the cache. This issue is called {\em cache
                 completeness}. A separate issue, {\em cache currency},
                 deals with the effect on client caches of updates
                 committed at the central database. We examine the
                 various performance tradeoffs and optimization issues
                 involved in addressing the questions of cache currency
                 and completeness using predicate descriptions and
                 suggest solutions that promote good dynamic behavior.
                 Lower query-response times, reduced message traffic,
                 higher server throughput, and better scalability are
                 some of the expected benefits of our approach over
                 commonly used relational server-side and object
                 ID-based or page-based client-side caching.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "cache completeness; cache currency; caching; multiple
                 clients; relational databases",
}

@Article{Stonebraker:1996:MWA,
  author =       "Michael Stonebraker and Paul M. Aoki and Witold Litwin
                 and Avi Pfeffer and Adam Sah and Jeff Sidell and Carl
                 Staelin and Andrew Yu",
  title =        "{Mariposa}: {A} Wide-Area Distributed Database
                 System",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "1",
  pages =        "48--63",
  month =        jan,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:36 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Aoki:Paul_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Litwin:Witold.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Pfeffer:Avi.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sah:Adam.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sidell:Jeff.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Staelin:Carl.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Stonebraker:Michael.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Yu:Andrew.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005001/60050048.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050048.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050048.ps.gz",
  abstract =     "The requirements of wide-area distributed database
                 systems differ dramatically from those of local-area
                 network systems. In a wide-area network (WAN)
                 configuration, individual sites usually report to
                 different system administrators, have different access
                 and charging algorithms, install site-specific data
                 type extensions, and have different constraints on
                 servicing remote requests. Typical of the last point
                 are production transaction environments, which are
                 fully engaged during normal business hours, and cannot
                 take on additional load. Finally, there may be many
                 sites participating in a WAN distributed DBMS.In this
                 world, a single program performing global query
                 optimization using a cost-based optimizer will not work
                 well. Cost-based optimization does not respond well to
                 site-specific type extension, access constraints,
                 charging algorithms, and time-of-day constraints.
                 Furthermore, traditional cost-based distributed
                 optimizers do not scale well to a large number of
                 possible processing sites. Since traditional
                 distributed DBMSs have all used cost-based optimizers,
                 they are not appropriate in a WAN environment, and a
                 new architecture is required. We have proposed and
                 implemented an economic paradigm as the solution to
                 these issues in a new distributed DBMS called Mariposa.
                 In this paper, we present the architecture and
                 implementation of Mariposa and discuss early feedback
                 on its operating characteristics.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "autonomy; databases; distributed systems; economic
                 site; name service; wide-area network",
}

@Article{Harris:1996:JAC,
  author =       "Evan P. Harris and Kotagiri Ramamohanarao",
  title =        "Join Algorithm Costs Revisited",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "1",
  pages =        "64--84",
  month =        jan,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:36 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Harris:Evan_P=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ramamohanarao:Kotagiri.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005001/60050064.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050064.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050064.ps.gz",
  abstract =     "A method of analysing join algorithms based upon the
                 time required to access, transfer and perform the
                 relevant CPU-based operations on a disk page is
                 proposed. The costs of variations of several of the
                 standard join algorithms, including nested block,
                 sort-merge, GRACE hash and hybrid hash, are presented.
                 For a given total buffer size, the cost of these join
                 algorithms depends on the parts of the buffer allocated
                 for each purpose. For example, when joining two
                 relations using the nested block join algorithm, the
                 amount of buffer space allocated for the outer and
                 inner relations can significantly affect the cost of
                 the join. Analysis of expected and experimental results
                 of various join algorithms show that a combination of
                 the optimal nested block and optimal GRACE hash join
                 algorithms usually provide the greatest cost benefit,
                 unless the relation size is a small multiple of the
                 memory size. Algorithms to quickly determine a buffer
                 allocation producing the minimal cost for each of these
                 algorithms are presented. When the relation size is a
                 small multiple of the amount of main memory available
                 (typically up to three to six times), the hybrid hash
                 join algorithm is preferable.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "join algorithms; minimisation; optimal buffer
                 allocation",
}

@Article{Ramamritham:1996:TCC,
  author =       "Krithi Ramamritham and Panos K. Chrysanthis",
  title =        "A taxonomy of correctness criteria in database
                 applications (*)",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "1",
  pages =        "85--97",
  month =        jan,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:36 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chrysanthis:Panos_K=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ramamritham:Krithi.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005001/60050085.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050085.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005001/60050085.ps.gz",
  abstract =     "Whereas serializability captures {\em database
                 consistency requirements\/} and {\em transaction
                 correctness properties\/} via a single notion, recent
                 research has attempted to come up with correctness
                 criteria that view these two types of requirements
                 independently. The search for more flexible correctness
                 criteria is partly motivated by the introduction of new
                 transaction models that extend the traditional atomic
                 transaction model. These extensions came about because
                 the atomic transaction model in conjunction with
                 serializability is found to be very constraining when
                 used in advanced applications (e.g., design databases)
                 that function in distributed, cooperative, and
                 heterogeneous environments. In this article we develop
                 a taxonomy of various {\em correctness criteria\/} that
                 focus on database consistency requirements and
                 transaction correctness properties from the viewpoint
                 of {\em what\/} the different dimensions of these two
                 are. This taxonomy allows us to categorize correctness
                 criteria that have been proposed in the literature. To
                 help in this categorization, we have applied a uniform
                 specification technique, based on ACTA, to express the
                 various criteria. Such a categorization helps shed
                 light on the similarities and differences between
                 different criteria and places them in perspective.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; database correctness criteria;
                 formal specifications; transaction processing",
}

@Article{Tsatalos:1996:GVT,
  author =       "Odysseas G. Tsatalos and Marvin H. Solomon and Yannis
                 E. Ioannidis",
  title =        "The {GMAP}: {A} Versatile Tool for Physical Data
                 Independence",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "2",
  pages =        "101--118",
  month =        apr,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:38 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/i/Ioannidis:Yannis_E=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Solomon:Marvin_H=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tsatalos:Odysseas_G=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005002/60050101.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050101.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050101.ps.gz",
  abstract =     "Physical data independence is touted as a central
                 feature of modern database systems. It allows users to
                 frame queries in terms of the logical structure of the
                 data, letting a query processor automatically translate
                 them into optimal plans that access physical storage
                 structures. Both relational and object-oriented
                 systems, however, force users to frame their queries in
                 terms of a logical schema that is directly tied to
                 physical structures. We present an approach that
                 eliminates this dependence. All storage structures are
                 defined in a declarative language based on relational
                 algebra as functions of a logical schema. We present an
                 algorithm, integrated with a conventional query
                 optimizer, that translates queries over this logical
                 schema into plans that access the storage structures.
                 We also show how to compile update requests into plans
                 that update all relevant storage structures
                 consistently and optimally. Finally, we report on
                 experiments with a prototype implementation of our
                 approach that demonstrate how it allows storage
                 structures to be tuned to the expected or observed
                 workload to achieve significantly better performance
                 than is possible with conventional techniques.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "indexing; materialized views; physical data
                 independence; physical database design",
}

@Article{Poulovassilis:1996:AQO,
  author =       "Alexandra Poulovassilis and Carol Small",
  title =        "Algebraic Query Optimisation for Database Programming
                 Languages",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "2",
  pages =        "119--132",
  month =        apr,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:38 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Poulovassilis:Alexandra.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Small:Carol.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005002/60050119.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050119.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050119.ps.gz",
  abstract =     "A major challenge still facing the designers and
                 implementors of database programming languages (DBPLs)
                 is that of query optimisation. We investigate algebraic
                 query optimisation techniques for DBPLs in the context
                 of a purely declarative functional language that
                 supports sets as first-class objects. Since the
                 language is computationally complete issues such as
                 non-termination of expressions and construction of
                 infinite data structures can be investigated, whilst
                 its declarative nature allows the issue of side effects
                 to be avoided and a richer set of equivalences to be
                 developed. The language has a well-defined semantics
                 which permits us to reason formally about the
                 properties of expressions, such as their equivalence
                 with other expressions and their termination. The
                 support of a set bulk data type enables much prior work
                 on the optimisation of relational languages to be
                 utilised. In the paper we first give the syntax of our
                 archetypal DBPL and briefly discuss its semantics. We
                 then define a small but powerful algebra of operators
                 over the set data type, provide some key equivalences
                 for expressions in these operators, and list
                 transformation principles for optimising expressions.
                 Along the way, we identify some caveats to well-known
                 equivalences for non-deductive database languages. We
                 next extend our language with two higher level
                 constructs commonly found in functional DBPLs: set
                 comprehensions and functions with known inverses. Some
                 key equivalences for these constructs are provided, as
                 are transformation principles for expressions in them.
                 Finally, we investigate extending our equivalences for
                 the set operators to the analogous operators over bags.
                 Although developed and formally proved in the context
                 of a functional language, our findings are directly
                 applicable to other DBPLs of similar expressiveness.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "algebraic manipulation; database management; database
                 programming languages; functional languages; query
                 optimisation",
}

@Article{Amiel:1996:TSR,
  author =       "Eric Amiel and Marie-Jo Bellosta and Eric Dujardin and
                 Eric Simon",
  title =        "Type-safe Relaxing of Schema Consistency Rules for
                 Flexible Modeling in {OODBMS}",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "2",
  pages =        "133--150",
  month =        apr,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:38 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Amiel:Eric.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Bellosta:Marie=Jo.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Dujardin:Eric.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Simon:Eric.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005002/60050133.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050133.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050133.ps.gz",
  abstract =     "Object-oriented databases enforce behavioral schema
                 consistency rules to guarantee type safety, i.e., that
                 no run-time type error can occur. When the schema must
                 evolve, some schema updates may violate these rules. In
                 order to maintain behavioral schema consistency,
                 traditional solutions require significant changes to
                 the types, the type hierarchy and the code of existing
                 methods. Such operations are very expensive in a
                 database context. To ease schema evolution, we propose
                 to support exceptions to the behavioral consistency
                 rules without sacrificing type safety. The basic idea
                 is to detect unsafe statements in a method code at
                 compile-time and check them at run-time. The run-time
                 check is performed by a specific clause that is
                 automatically inserted around unsafe statements. This
                 check clause warns the programmer of the safety problem
                 and lets him provide exception-handling code. Schema
                 updates can therefore be performed with only minor
                 changes to the code of methods.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "contravariance; covariance; object-oriented databases;
                 schema evolution; type safety",
  xxtitle =      "Type-safe relaxing of schema consistency rules for
                 flexible modelling in {OODBMS}",
}

@Article{Fang:1996:EOB,
  author =       "Doug Fang and Shahram Ghandeharizadeh and Dennis
                 McLeod",
  title =        "An experimental object-based sharing system for
                 networked databases",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "2",
  pages =        "151--165",
  month =        apr,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:38 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Fang:Doug.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Ghandeharizadeh:Shahram.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005002/60050151.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050151.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005002/60050151.ps.gz;
                 http://link.springer.de/link/service/journals/00778/tocs/mailto: HREF="mailto:helpdesk@link.springer.de">helpdesk@link.springer.de",
  abstract =     "An approach and mechanism for the transparent sharing
                 of objects in an environment of interconnected
                 (networked), autonomous database systems is presented.
                 An experimental prototype system has been designed and
                 implemented, and an analysis of its performance
                 conducted. Previous approaches to sharing in this
                 environment typically rely on the use of a global,
                 integrated conceptual database schema; users and
                 applications must pose queries at this new level of
                 abstraction to access remote information. By contrast,
                 our approach provides a mechanism that allows users to
                 import remote objects directly into their local
                 database transparently; access to remote objects is
                 virtually the same as access to local objects. The
                 experimental prototype system that has been designed
                 and implemented is based on the Iris and Omega
                 object-based database management systems; this system
                 supports the sharing of data and meta-data objects
                 (information units) as well as units of behavior. The
                 results of experiments conducted to evaluate the
                 performance of our mechanism demonstrate the
                 feasibility of database transparent object sharing in a
                 federated environment, and provide insight into the
                 performance overhead and tradeoffs involved.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database system interoperability; experimental
                 prototype benchmarking; object sharing",
  xxtitle =      "An Experimental System for Object-Based Sharing in
                 Federated Databases",
}

@Article{Dey:1996:CTR,
  author =       "Debabrata Dey and Terence M. Barron and Veda C.
                 Storey",
  title =        "A Complete Temporal Relational Algebra",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "3",
  pages =        "167--180",
  month =        aug,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Barron:Terence_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Dey:Debabrata.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Storey:Veda_C=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005003/60050167.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050167.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050167.ps.gz",
  abstract =     "Various temporal extensions to the relational model
                 have been proposed. All of these, however, deviate
                 significantly from the original relational model. This
                 paper presents a temporal extension of the relational
                 algebra that is not significantly different from the
                 original relational model, yet is at least as
                 expressive as any of the previous approaches. This
                 algebra employs multidimensional tuple time-stamping to
                 capture the complete temporal behavior of data. The
                 basic relational operations are redefined as consistent
                 extensions of the existing operations in a manner that
                 preserves the basic algebraic equivalences of the
                 snapshot (i.e., conventional static) algebra. A new
                 operation, namely {\em temporal projection}, is
                 introduced. The complete update semantics are formally
                 specified and aggregate functions are defined. The
                 algebra is closed, and reduces to the snapshot algebra.
                 It is also shown to be at least as expressive as the
                 calculus-based temporal query language TQuel. In order
                 to assess the algebra, it is evaluated using a set of
                 twenty-six criteria proposed in the literature, and
                 compared to existing temporal relational algebras. The
                 proposed algebra appears to satisfy more criteria than
                 any other existing algebra.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "historical databases; relational algebra; temporal
                 databases; transaction time; valid time",
  remark =       "Check month: July or August??",
}

@Article{Shyy:1996:DIK,
  author =       "Yuh-Ming Shyy and Javier Arroyo and Stanley Y. W. Su
                 and Herman Lam",
  title =        "The Design and Implementation of {K}: {A} High-Level
                 Knowledge-Base Programming Language of {OSAM*.KBMS}",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "3",
  pages =        "181--195",
  month =        aug,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Arroyo:Javier.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lam:Herman.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Shyy:Yuh=Ming.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Su:Stanley_Y=_W=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005003/60050181.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050181.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050181.ps.gz",
  abstract =     "The OSAM*.KBMS is a knowledge-base management system,
                 or the so-called next-generation database management
                 system, for non-traditional data/knowledge-intensive
                 applications. In order to define, query, and manipulate
                 a knowledge base, as well as to write codes to
                 implement any application system, we have developed an
                 object-oriented knowledge-base programming language
                 called K to serve as the high-level interface of
                 OSAM*.KBMS. This paper presents the design of K, its
                 implementation, and its supporting KBMS developed at
                 the Database Systems Research and Development Center of
                 the University of Florida.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "abstractions; association patterns; knowledge-base
                 programming language; object-oriented knowledge model;
                 structural associations",
  remark =       "Check month: July or August??",
}

@Article{Harder:1996:APS,
  author =       "Theo H{\"a}rder and Joachim Reinert",
  title =        "Access Path Support for Referential Integrity in
                 {SQL2}",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "3",
  pages =        "196--214",
  month =        aug,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/H=auml=rder:Theo.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Reinert:Joachim.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005003/60050196.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050196.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050196.ps.gz",
  abstract =     "The relational model of data incorporates fundamental
                 assertions for entity integrity and referential
                 integrity. Recently, these so-called relational
                 invariants were more precisely specified by the new
                 SQL2 standard. Accordingly, they have to be guaranteed
                 by a relational DBMS to its users and, therefore, all
                 issues of semantics and implementation became very
                 important. The specification of referential integrity
                 embodies quite a number of complications including the
                 MATCH clause and a collection of referential actions.
                 In particular, $\hbox{{\tt MATCH PARTIAL}}$ turns out
                 to be hard to understand and, if applied, difficult and
                 expensive to maintain. In this paper, we identify the
                 functional requirements for preserving referential
                 integrity. At a level free of implementational
                 considerations, the number and kinds of searches
                 necessary for referential integrity maintenance are
                 derived. Based on these findings, our investigation is
                 focused on the question of how the functional
                 requirements can be supported by implementation
                 concepts in an efficient way. We determine the search
                 cost for referential integrity maintenance (in terms of
                 page references) for various possible access path
                 structures. Our main result is that a combined access
                 path structure is the most appropriate for checking the
                 regular MATCH option, whereas $\hbox{{\tt MATCH
                 PARTIAL}}$ requires very expensive and complicated
                 check procedures. If it cannot be avoided at all, the
                 best support is achieved by a combination of multiple
                 $\mbox{B}^*$-trees.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access path support; MATCH clause; referential
                 integrity; relational databases; SQL2",
  remark =       "Check month: July or August??",
}

@Article{Ooi:1996:INE,
  author =       "Beng Chin Ooi and Jiawei Han and Hongjun Lu and Kian
                 Lee Tan",
  title =        "Index Nesting --- An Efficient Approach to Indexing in
                 Object-Oriented Databases",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "3",
  pages =        "215--228",
  month =        aug,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Han:Jiawei.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lu:Hongjun.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/o/Ooi:Beng_Chin.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tan:Kian=Lee.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005003/60050215.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050215.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005003/60050215.ps.gz;
                 http://link.springer.de/link/service/journals/00778/tocs/mailto: HREF="mailto:helpdesk@link.springer.de">helpdesk@link.springer.de",
  abstract =     "In object-oriented database systems where the concept
                 of the superclass-subclass is supported, an instance of
                 a subclass is also an instance of its superclass.
                 Consequently, the access scope of a query against a
                 class in general includes the access scope of all its
                 subclasses, unless specified otherwise. An index to
                 support superclass-subclass relationship efficiently
                 must provide efficient associative retrievals of
                 objects from a single class or from several classes in
                 a class hierarchy. This paper presents an efficient
                 index called the hierarchical tree (the H-tree). For
                 each class, an H-tree is maintained, allowing efficient
                 search on a single class. These H-trees are
                 appropriately linked to capture the superclass-subclass
                 relationships, thus allowing efficient retrievals of
                 instances from a class hierarchy. Both experimental and
                 analytical results indicate that the H-tree is an
                 efficient indexing structure.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "indexing structures; OODB; query retrieval",
  remark =       "Check month: July or August??",
}

@Article{Antoshenkov:1996:QPO,
  author =       "Gennady Antoshenkov and Mohamed Ziauddin",
  title =        "Query Processing and Optimization in {Oracle Rdb}",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "4",
  pages =        "229--237",
  month =        dec,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Antoshenkov:Gennady.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Ziauddin:Mohamed.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005004/60050229.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050229.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050229.ps.gz",
  abstract =     "This paper contains an overview of the technology used
                 in the query processing and optimization component of
                 Oracle Rdb, a relational database management system
                 originally developed by Digital Equipment Corporation
                 and now under development by Oracle Corporation. Oracle
                 Rdb is a production system that supports the most
                 demanding database applications, runs on multiple
                 platforms and in a variety of environments.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "dynamic optimization; optimizer; query transformation;
                 relational database; sampling",
}

@Article{Mylopoulos:1996:BKB,
  author =       "John Mylopoulos and Vinay K. Chaudhri and Dimitris
                 Plexousakis and Adel Shrufi and Thodoros Topologlou",
  title =        "Building Knowledge Base Management Systems",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "4",
  pages =        "238--263",
  month =        dec,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chaudhri:Vinay_K=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mylopoulos:John.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Plexousakis:Dimitris.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Shrufi:Adel.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Topaloglou:Thodoros.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005004/60050238.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050238.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050238.ps.gz",
  abstract =     "Advanced applications in fields such as CAD, software
                 engineering, real-time process control, corporate
                 repositories and digital libraries require the
                 construction, efficient access and management of large,
                 shared knowledge bases. Such knowledge bases cannot be
                 built using existing tools such as expert system
                 shells, because these do not scale up, nor can they be
                 built in terms of existing database technology, because
                 such technology does not support the rich
                 representational structure and inference mechanisms
                 required for knowledge-based systems. This paper
                 proposes a generic architecture for a knowledge base
                 management system intended for such applications. The
                 architecture assumes an object-oriented knowledge
                 representation language with an assertional sublanguage
                 used to express constraints and rules. It also provides
                 for general-purpose deductive inference and
                 special-purpose temporal reasoning. Results reported in
                 the paper address several knowledge base management
                 issues. For storage management, a new method is
                 proposed for generating a logical schema for a given
                 knowledge base. Query processing algorithms are offered
                 for semantic and physical query optimization, along
                 with an enhanced cost model for query cost estimation.
                 On concurrency control, the paper describes a novel
                 concurrency control policy which takes advantage of
                 knowledge base structure and is shown to outperform
                 two-phase locking for highly structured knowledge bases
                 and update-intensive transactions. Finally, algorithms
                 for compilation and efficient processing of constraints
                 and rules during knowledge base operations are
                 described. The paper describes original results,
                 including novel data structures and algorithms, as well
                 as preliminary performance evaluation data. Based on
                 these results, we conclude that knowledge base
                 management systems which can accommodate large
                 knowledge bases are feasible.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; constraint enforcement; knowledge
                 base management systems; rule management; storage
                 management",
}

@Article{Becker:1996:AOM,
  author =       "Bruno Becker and Stephan Gschwind and Thomas Ohler and
                 Bernhard Seeger and Peter Widmayer",
  title =        "An Asymptotically Optimal Multiversion {B}-Tree",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "4",
  pages =        "264--275",
  month =        dec,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Becker:Bruno.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Gschwind:Stephan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/o/Ohler:Thomas.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Seeger:Bernhard.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Widmayer:Peter.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005004/60050264.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050264.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050264.ps.gz",
  abstract =     "In a variety of applications, we need to keep track of
                 the development of a data set over time. For
                 maintaining and querying these multiversion data
                 efficiently, external storage structures are an
                 absolute necessity. We propose a multiversion B-tree
                 that supports insertions and deletions of data items at
                 the current version and range queries and exact match
                 queries for any version, current or past. Our
                 multiversion B-tree is asymptotically optimal in the
                 sense that the time and space bounds are asymptotically
                 the same as those of the (single-version) B-tree in the
                 worst case. The technique we present for transforming a
                 (single-version) B-tree into a multiversion B-tree is
                 quite general: it applies to a number of hierarchical
                 external access structures with certain properties
                 directly, and it can be modified for others.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access methods; information systems; physical design;
                 versioned data",
}

@Article{Kashyap:1996:SSS,
  author =       "Vipul Kashyap and Amit P. Sheth",
  title =        "Semantic and Schematic Similarities Between Database
                 Objects: {A} Context-Based Approach",
  journal =      j-VLDB-J,
  volume =       "5",
  number =       "4",
  pages =        "276--304",
  month =        dec,
  year =         "1996",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:39 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb5.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t6005004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kashyap:Vipul.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sheth:Amit_P=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/6005004/60050276.htm;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050276.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/6005004/60050276.ps.gz;
                 http://link.springer.de/link/service/journals/00778/tocs/mailto: HREF="mailto:helpdesk@link.springer.de">helpdesk@link.springer.de",
  abstract =     "In a multidatabase system, schematic conflicts between
                 two objects are usually of interest only when the
                 objects have some semantic similarity. We use the
                 concept of {\em semantic proximity}, which is
                 essentially an {\em abstraction/mapping\/} between the
                 domains of the two objects associated with the {\em
                 context of comparison}. An explicit though partial
                 context representation is proposed and the specificity
                 relationship between contexts is defined. The contexts
                 are organized as a meet semi-lattice and associated
                 operations like the greatest lower bound are defined.
                 The context of comparison and the type of abstractions
                 used to relate the two objects form the basis of a
                 semantic taxonomy. At the {\em semantic level}, the
                 intensional description of database objects provided by
                 the context is expressed using description logics. The
                 terms used to construct the contexts are obtained from
                 {\em domain-specific ontologies}. {\em Schema
                 correspondences\/} are used to store mappings from the
                 semantic level to the data level and are associated
                 with the respective contexts. Inferences about database
                 content at the federation level are modeled as changes
                 in the context and the associated schema
                 correspondences. We try to reconcile the dual
                 (schematic and semantic) perspectives by enumerating
                 {\em possible semantic similarities\/} between objects
                 having schema and data conflicts, and modeling schema
                 correspondences as the projection of semantic proximity
                 {\em with respect to (wrt)\/} context.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Evangelidis:1997:HTM,
  author =       "Georgios Evangelidis and David B. Lomet and Betty
                 Salzberg",
  title =        "The {hB} $^{\Pi}$-tree: a multi-attribute index
                 supporting concurrency, recovery and node
                 consolidation",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "1",
  pages =        "1--25",
  month =        feb,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:40 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/e/Evangelidis:Georgios.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lomet:David_B=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Salzberg:Betty.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006001/70060001.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060001.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060001.ps.gz",
  abstract =     "We propose a new multi-attribute index. Our approach
                 combines the hB-tree, a multi-attribute index, and the
                 $\Pi$-tree, an abstract index which offers efficient
                 concurrency and recovery methods. We call the resulting
                 method the hB $^\Pi$-tree. We describe several versions
                 of the hB $^\Pi$-tree, each using a different
                 node-splitting and index-term-posting algorithm. We
                 also describe a new node deletion algorithm. We have
                 implemented all the versions of the hB $^\Pi$-tree. Our
                 performance results show that even the version that
                 offers no performance guarantees, actually performs
                 very well in terms of storage utilization, index size
                 (fan-out), exact-match and range searching, under
                 various data types and distributions. We have also
                 shown that our index is fairly insensitive to increases
                 in dimension. Thus, it is suitable for indexing
                 high-dimensional applications. This property and the
                 fact that all our versions of the hB $^\Pi$-tree can
                 use the $\Pi$-tree concurrency and recovery algorithms
                 make the hB $^\Pi$-tree a promising candidate for
                 inclusion in a general-purpose DBMS.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency; multi-attribute index; node
                 consolidation; recovery",
  remark =       "Check month: January or February??",
}

@Article{Antoshenkov:1997:DBO,
  author =       "Gennady Antoshenkov",
  title =        "Dictionary-based order-preserving string compression
                 (*)",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "1",
  pages =        "26--39",
  month =        feb,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:40 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Antoshenkov:Gennady.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006001/70060026.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060026.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060026.ps.gz",
  abstract =     "As no database exists without indexes, no index
                 implementation exists without order-preserving key
                 compression, in particular, without prefix and tail
                 compression. However, despite the great potentials of
                 making indexes smaller and faster, application of
                 general compression methods to ordered data sets has
                 advanced very little. This paper demonstrates that the
                 fast dictionary-based methods can be applied to
                 order-preserving compression almost with the same
                 freedom as in the general case. The proposed new
                 technology has the same speed and a compression rate
                 only marginally lower than the traditional
                 order-indifferent dictionary encoding. Procedures for
                 encoding and generating the encode tables are described
                 covering such order-related features as ordered data
                 set restrictions, sensitivity and insensitivity to a
                 character position, and one-symbol encoding of each
                 frequent trailing character sequence. The experimental
                 results presented demonstrate five-folded compression
                 on real-life data sets and twelve-folded compression on
                 Wisconsin benchmark text fields.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "indexing; order-preserving key compression",
  remark =       "Check month: January or February??",
}

@Article{Singhal:1997:ALB,
  author =       "Vigyan Singhal and Alan Jay Smith",
  title =        "Analysis of Locking Behavior in Three Real Database
                 Systems",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "1",
  pages =        "40--52",
  month =        feb,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:40 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Singhal:Vigyan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Smith:Alan_Jay.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006001/70060040.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060040.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060040.ps.gz",
  abstract =     "Concurrency control is essential to the correct
                 functioning of a database due to the need for correct,
                 reproducible results. For this reason, and because
                 concurrency control is a well-formulated problem, there
                 has developed an enormous body of literature studying
                 the performance of concurrency control algorithms. Most
                 of this literature uses either analytic modeling or
                 random number-driven simulation, and explicitly or
                 implicitly makes certain assumptions about the behavior
                 of transactions and the patterns by which they set and
                 unset locks. Because of the difficulty of collecting
                 suitable measurements, there have been only a few
                 studies which use trace-driven simulation, and still
                 less study directed toward the characterization of
                 concurrency control behavior of real workloads. In this
                 paper, we present a study of three database workloads,
                 all taken from IBM DB2 relational database systems
                 running commercial applications in a production
                 environment. This study considers topics such as
                 frequency of locking and unlocking, deadlock and
                 blocking, duration of locks, types of locks,
                 correlations between applications of lock types,
                 two-phase versus non-two-phase locking, when locks are
                 held and released, etc. In each case, we evaluate the
                 behavior of the workload relative to the assumptions
                 commonly made in the research literature and discuss
                 the extent to which those assumptions may or may not
                 lead to erroneous conclusions.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; trace-driven simulation; workload
                 characterization",
  remark =       "Check month: January or February??",
}

@Article{Mehta:1997:DPS,
  author =       "Manish Mehta and David J. DeWitt",
  title =        "Data placement in shared-nothing parallel database
                 systems (*)",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "1",
  pages =        "53--72",
  month =        feb,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:40 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/DeWitt:David_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mehta:Manish.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006001/70060053.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060053.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006001/70060053.ps.gz;
                 http://link.springer.de/link/service/journals/00778/tocs/mailto: HREF="mailto:helpdesk@link.springer.de">helpdesk@link.springer.de",
  abstract =     "Data placement in shared-nothing database systems has
                 been studied extensively in the past and various
                 placement algorithms have been proposed. However, there
                 is no consensus on the most efficient data placement
                 algorithm and placement is still performed manually by
                 a database administrator with periodic reorganization
                 to correct mistakes. This paper presents the first
                 comprehensive simulation study of data placement issues
                 in a shared-nothing system. The results show that
                 current hardware technology trends have significantly
                 changed the performance tradeoffs considered in past
                 studies. A simplistic data placement strategy based on
                 the new results is developed and shown to perform well
                 for a variety of workloads.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "declustering; disk allocation; resource allocation;
                 resource scheduling",
  remark =       "Check month: January or February??",
}

@Article{Papazoglou:1997:DMO,
  author =       "Mike P. Papazoglou and Bernd J. Kr{\"a}mer",
  title =        "A Database Model for Object Dynamics",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "2",
  pages =        "73--96",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:41 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition. See erratum
                 \cite{Papazoglou:1997:EDM}.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kr=auml=mer:Bernd_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Papazoglou:Mike_P=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006002/70060073.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060073.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060073.ps.gz",
  abstract =     "To effectively model complex applications in which
                 constantly changing situations can be represented, a
                 database system must be able to support the runtime
                 specification of structural and behavioral nuances for
                 objects on an individual or group basis. This paper
                 introduces the role mechanism as an extension of
                 object-oriented databases to support unanticipated
                 behavioral oscillations for objects that may attain
                 many types and share a single object identity. A role
                 refers to the ability to represent object dynamics by
                 seamlessly integrating idiosyncratic behavior, possibly
                 in response to external events, with pre-existing
                 object behavior specified at instance creation time. In
                 this manner, the same object can simultaneously be an
                 instance of different classes which symbolize the
                 different roles that this object assumes. The role
                 concept and its underlying linguistic scheme simplify
                 the design requirements of complex applications that
                 need to create and manipulate dynamic objects.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "dynamic class hierarchy; dynamic object
                 re-classification; object migration; object role model;
                 object-oriented database systems",
  remark =       "Check month: May or August??",
}

@Article{Catarci:1997:GIH,
  author =       "Tiziana Catarci and Giuseppe Santucci and John
                 Cardiff",
  title =        "Graphical interaction with heterogeneous databases
                 (*)",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "2",
  pages =        "97--120",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:41 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Cardiff:John.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Catarci:Tiziana.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Santucci:Giuseppe.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006002/70060097.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060097.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060097.ps.gz",
  abstract =     "During the past few years our research efforts have
                 been inspired by two different needs. On one hand, the
                 number of non-expert users accessing databases is
                 growing apace. On the other, information systems will
                 no longer be characterized by a single centralized
                 architecture, but rather by several heterogeneous
                 component systems. In order to address such needs we
                 have designed a new query system with both
                 user-oriented and multidatabase features. The system's
                 main components are an adaptive visual interface,
                 providing the user with different and interchangeable
                 interaction modalities, and a ``translation layer'',
                 which creates and offers to the user the illusion of a
                 single homogeneous schema out of several heterogeneous
                 components. Both components are founded on a common
                 ground, i.e. a formally defined and semantically rich
                 data model, the Graph Model, and a minimal set of
                 Graphical Primitives, in terms of which general query
                 operations may be visually expressed. The Graph Model
                 has a visual syntax, so that graphical operations can
                 be applied on its components without unnecessary
                 mappings, and an object-based semantics. The aim of
                 this paper is twofold. We first present an overall view
                 of the system architecture and then give a
                 comprehensive description of the lower part of the
                 system itself. In particular, we show how schemata
                 expressed in different data models can be translated in
                 terms of Graph Model, possibly by exploiting reverse
                 engineering techniques. Moreover, we show how mappings
                 can be established between well-known query languages
                 and the Graphical Primitives. Finally, we describe in
                 detail how queries expressed by using the Graphical
                 Primitives can be translated in terms of relational
                 expressions so to be processed by actual DBMSs.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  remark =       "Check month: May or August??",
}

@Article{Chen:1997:AHF,
  author =       "Ming-Syan Chen and Hui-I Hsiao and Philip S. Yu",
  title =        "On Applying Hash Filters to Improving the Execution of
                 Multi-Join Queries",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "2",
  pages =        "121--131",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:41 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chen:Ming=Syan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Hsiao:Hui=I.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Yu:Philip_S=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006002/70060121.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060121.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060121.ps.gz",
  abstract =     "In this paper, we explore an approach of interleaving
                 a bushy execution tree with hash filters to improve the
                 execution of multi-join queries. Similar to semi-joins
                 in distributed query processing, hash filters can be
                 applied to eliminate non-matching tuples from joining
                 relations before the execution of a join, thus reducing
                 the join cost. Note that hash filters built in
                 different execution stages of a bushy tree can have
                 different costs and effects. The effect of hash filters
                 is evaluated first. Then, an efficient scheme to
                 determine an effective sequence of hash filters for a
                 bushy execution tree is developed, where hash filters
                 are built and applied based on the join sequence
                 specified in the bushy tree so that not only is the
                 reduction effect optimized but also the cost associated
                 is minimized. Various schemes using hash filters are
                 implemented and evaluated via simulation. It is
                 experimentally shown that the application of hash
                 filters is in general a very powerful means to improve
                 the execution of multi-join queries, and the
                 improvement becomes more prominent as the number of
                 relations in a query increases.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "bushy trees; hash filters; parallel query processing;
                 sort-merge joins",
  remark =       "Check month: May or August??",
}

@Article{Ioannidis:1997:PQO,
  author =       "Yannis E. Ioannidis and Raymond T. Ng and Kyuseok Shim
                 and Timos K. Sellis",
  title =        "Parametric Query Optimization",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "2",
  pages =        "132--151",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:41 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/i/Ioannidis:Yannis_E=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Ng:Raymond_T=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sellis:Timos_K=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Shim:Kyuseok.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006002/70060132.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060132.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060132.ps.gz",
  abstract =     "In most database systems, the values of many important
                 run-time parameters of the system, the data, or the
                 query are unknown at query optimization time.
                 Parametric query optimization attempts to identify at
                 compile time several execution plans, each one of which
                 is optimal for a subset of all possible values of the
                 run-time parameters. The goal is that at run time, when
                 the actual parameter values are known, the appropriate
                 plan should be identifiable with essentially no
                 overhead. We present a general formulation of this
                 problem and study it primarily for the buffer size
                 parameter. We adopt randomized algorithms as the main
                 approach to this style of optimization and enhance them
                 with a {\em sideways information passing\/} feature
                 that increases their effectiveness in the new task.
                 Experimental results of these enhanced algorithms show
                 that they optimize queries for large numbers of buffer
                 sizes in the same time needed by their conventional
                 versions for a single buffer size, without much
                 sacrifice in the output quality and with essentially
                 zero run-time overhead.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  remark =       "Check month: May or August??",
}

@Article{Mehrotra:1997:CCH,
  author =       "Sharad Mehrotra and Henry F. Korth and Avi
                 Silberschatz",
  title =        "Concurrency Control in Hierarchical Multidatabase
                 Systems",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "2",
  pages =        "152--172",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:41 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Korth:Henry_F=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mehrotra:Sharad.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Silberschatz:Abraham.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006002/70060152.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060152.pdf;
                 http://link.springer.de/link/service/journals/00778/papers/7006002/70060152.ps.gz;
                 http://link.springer.de/link/service/journals/00778/tocs/mailto: HREF="mailto:helpdesk@link.springer.de">helpdesk@link.springer.de",
  abstract =     "Over the past decade, significant research has been
                 done towards developing transaction management
                 algorithms for multidatabase systems. Most of this work
                 assumes a monolithic architecture of the multidatabase
                 system with a single software module that follows a
                 single transaction management algorithm to ensure the
                 consistency of data stored in the local databases. This
                 monolithic architecture is not appropriate in a
                 multidatabase environment where the system spans
                 multiple different organizations that are distributed
                 over various geographically distant locations. In this
                 paper, we propose an alternative multidatabase
                 transaction management architecture, where the system
                 is hierarchical in nature. Hierarchical architecture
                 has consequences on the design of transaction
                 management algorithms. An implication of the
                 architecture is that the transaction management
                 algorithms followed by a multidatabase system must be
                 {\em composable\/} --- that is, it must be possible to
                 incorporate individual multidatabase systems as
                 elements in a larger multidatabase system. We present a
                 hierarchical architecture for a multidatabase
                 environment and develop techniques for concurrency
                 control in such systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; database management; distributed
                 databases; multidatabase management",
  remark =       "Check month: May or August??",
  xxauthor =     "Sharad Mehrotra and Henry F. Korth and Abraham
                 Silberschatz",
}

@Article{Cobb:1997:IOT,
  author =       "Edward E. Cobb",
  title =        "The impact of object technology on commercial
                 transaction processing",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "3",
  pages =        "173--190",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:42 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Businesses today are searching for information
                 solutions that enable them to compete in the global
                 marketplace. To minimize risk, these solutions must
                 build on existing investments, permit the best
                 technology to be applied to the problem, and be
                 manageable. Object technology, with its promise of
                 improved productivity and quality in application
                 development, delivers these characteristics but, to
                 date, its deployment in commercial business
                 applications has been limited. One possible reason is
                 the absence of the transaction paradigm, widely used in
                 commercial environments and essential for reliable
                 business applications. For object technology to be a
                 serious contender in the construction of these
                 solutions requires: --- technology for transactional
                 objects. In December 1994, the Object Management Group
                 adopted a specification for an object {\em transaction
                 service\/} (OTS). The OTS specifies mechanisms for
                 defining and manipulating transactions. Though derived
                 from the X/Open distributed transaction processing
                 model, OTS contains additional enhancements
                 specifically designed for the object environment.
                 Similar technology from Microsoft appeared at the end
                 of 1995. --- methodologies for building new business
                 systems from existing parts. Business process
                 re-engineering is forcing businesses to improve their
                 operations which bring products to market. {\em
                 Workflow computing}, when used in conjunction with {\em
                 ``object wrappers''\/} provides tools to both define
                 and track execution of business processes which
                 leverage existing applications and infrastructure. --
                 an execution environment which satisfies the
                 requirements of the operational needs of the business.
                 Transaction processing (TP) monitor technology, though
                 widely accepted for mainframe transaction processing,
                 has yet to enjoy similar success in the client/server
                 marketplace. Instead the database vendors, with their
                 extensive tool suites, dominate. As object brokers
                 mature they will require many of the functions of
                 today's TP monitors. Marrying these two technologies
                 can produce a robust execution environment which offers
                 a superior alternative for building and deploying
                 client/server applications.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "objects; transaction processing; workflow",
}

@Article{Cobb:1997:ITC,
  author =       "Edward E. Cobb",
  title =        "The Impact of Technology on Commercial Transaction
                 Processing",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "3",
  pages =        "173--190",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 10:11:57 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0006003.htm;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Cobb:Edward_E=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006003/70060173.htm",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  remark =       "Check month: May or August??",
  xxtitle =      "The impact of object technology on commercial
                 transaction processing",
}

@Article{Steinbrunn:1997:HRO,
  author =       "Michael Steinbrunn and Guido Moerkotte and Alfons
                 Kemper",
  title =        "Heuristic and Randomized Optimization for the Join
                 Ordering Problem",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "3",
  pages =        "191--208",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:42 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0006003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kemper:Alfons.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Moerkotte:Guido.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Steinbrunn:Michael.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006003/70060191.htm",
  abstract =     "Recent developments in database technology, such as
                 deductive database systems, have given rise to the
                 demand for new, cost-effective optimization techniques
                 for join expressions. In this paper many different
                 algorithms that compute approximate solutions for
                 optimizing join orders are studied since traditional
                 dynamic programming techniques are not appropriate for
                 complex problems. Two possible solution spaces, the
                 space of left-deep and bushy processing trees, are
                 evaluated from a statistical point of view. The result
                 is that the common limitation to left-deep processing
                 trees is only advisable for certain join graph types.
                 Basically, optimizers from three classes are analysed:
                 heuristic, randomized and genetic algorithms. Each one
                 is extensively scrutinized with respect to its working
                 principle and its fitness for the desired application.
                 It turns out that randomized and genetic algorithms are
                 well suited for optimizing join expressions. They
                 generate solutions of high quality within a reasonable
                 running time. The benefits of heuristic optimizers,
                 namely the short running time, are often outweighed by
                 merely moderate optimization performance.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "genetic algorithms; heuristic algorithms; join
                 ordering; query optimization; randomized algorithms",
  remark =       "Check month: May or August??",
}

@Article{Panagos:1997:SRC,
  author =       "Euthimios Panagos and Alexandros Biliris",
  title =        "Synchronization and Recovery in a Client-Server
                 Storage System",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "3",
  pages =        "209--223",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:42 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0006003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Biliris:Alexandros.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Panagos:Euthimios.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006003/70060209.htm",
  abstract =     "Client-server object-oriented database management
                 systems differ significantly from traditional
                 centralized systems in terms of their architecture and
                 the applications they target. In this paper, we present
                 the client-server architecture of the EOS storage
                 manager and we describe the concurrency control and
                 recovery mechanisms it employs. EOS offers a
                 semi-optimistic locking scheme based on the
                 multi-granularity two-version two-phase locking
                 protocol. Under this scheme, multiple concurrent
                 readers are allowed to access a data item while it is
                 being updated by a single writer. Recovery is based on
                 write-ahead redo-only logging. Log records are
                 generated at the clients and they are shipped to the
                 server during normal execution and at transaction
                 commit. Transaction rollback is fast because there are
                 no updates that have to be undone, and recovery from
                 system crashes requires only one scan of the log for
                 installing the changes made by transactions that
                 committed before the crash. We also present a
                 preliminary performance evaluation of the
                 implementation of the above mechanisms.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "checkpoint; client-server architecture; concurrency
                 control; locking; logging; object management; recovery;
                 transaction management",
  remark =       "Check month: May or August??",
}

@Article{Lomet:1997:CRI,
  author =       "David B. Lomet and Betty Salzberg",
  title =        "Concurrency and Recovery for Index Trees",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "3",
  pages =        "224--240",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:42 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0006003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lomet:David_B=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Salzberg:Betty.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006003/70060224.htm",
  abstract =     "Although many suggestions have been made for
                 concurrency in B$^+$-trees, few of these have
                 considered recovery as well. We describe an approach
                 which provides high concurrency while preserving
                 well-formed trees across system crashes. Our approach
                 works for a class of index trees that is a
                 generalization of the B$^{\rm link}$-tree. This class
                 includes some multi-attribute indexes and temporal
                 indexes. Structural changes in an index tree are
                 decomposed into a sequence of atomic actions, each one
                 leaving the tree well-formed and each working on a
                 separate level of the tree. All atomic actions on
                 levels of the tree above the leaf level are independent
                 of database transactions, and so are of short duration.
                 Incomplete structural changes are detected in normal
                 operations and trigger completion.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access methods; B-trees; concurrency; indexing;
                 recovery",
  remark =       "Check month: May or August??",
}

@Article{Haas:1997:STA,
  author =       "Laura M. Haas and Michael J. Carey and Miron Livny and
                 Amit Shukla",
  title =        "Seeking the truth about {\em ad hoc\/} join costs",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "3",
  pages =        "241--256",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:42 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0006003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Carey:Michael_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Haas:Laura_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Livny:Miron.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Shukla:Amit.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006003/70060241.htm",
  abstract =     "In this paper, we re-examine the results of prior work
                 on methods for computing {\em ad hoc\/} joins. We
                 develop a detailed cost model for predicting join
                 algorithm performance, and we use the model to develop
                 cost formulas for the major {\em ad hoc\/} join methods
                 found in the relational database literature. We show
                 that various pieces of ``common wisdom'' about join
                 algorithm performance fail to hold up when analyzed
                 carefully, and we use our detailed cost model to derive
                 optimal buffer allocation schemes for each of the join
                 methods examined here. We show that optimizing their
                 buffer allocations can lead to large performance
                 improvements, e.g., as much as a 400\% improvement in
                 some cases. We also validate our cost model's
                 predictions by measuring an actual implementation of
                 each join algorithm considered. The results of this
                 work should be directly useful to implementors of
                 relational query optimizers and query processing
                 systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "buffer allocation; cost models; join methods;
                 optimization; performance",
  remark =       "Check month: May or August??",
}

@Article{Papazoglou:1997:EDM,
  author =       "Mike P. Papazoglou and Bernd J. Kr{\"a}mer",
  title =        "Erratum --- {A} database model for object dynamics",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "3",
  pages =        "257--260",
  month =        aug,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:42 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0006003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition. See \cite{Papazoglou:1997:DMO}.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kr=auml=mer:Bernd_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Papazoglou:Mike_P=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006003/70060257.htm",
  abstract =     "Due to a technical error, some figures of the above
                 paper were not reproduced satisfactorily. They are
                 printed again below:",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  remark =       "Check month: May or August??",
}

@Article{Fahl:1997:QPO,
  author =       "Gustav Fahl and Tore Risch",
  title =        "Query Processing Over Object Views of Relational
                 Data",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "4",
  pages =        "261--281",
  month =        nov,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:44 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Fahl:Gustav.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Risch:Tore.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006004/70060261.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006004/70060261.pdf",
  abstract =     "This paper presents an approach to {\em object view\/}
                 management for relational databases. Such a view
                 mechanism makes it possible for users to transparently
                 work with data in a relational database as if it was
                 stored in an object-oriented (OO) database. A query
                 against the object view is translated to one or several
                 queries against the relational database. The results of
                 these queries are then processed to form an answer to
                 the initial query. The approach is not restricted to a
                 `pure' object view mechanism for the relational data,
                 since the object view can also store its own data and
                 methods. Therefore it must be possible to process
                 queries that combine local data residing in the object
                 view with data retrieved from the relational database.
                 We discuss the key issues when object views of
                 relational databases are developed, namely: how to map
                 relational structures to sub-type/supertype hierarchies
                 in the view, how to represent relational database
                 access in OO query plans, how to provide the concept of
                 object identity in the view, how to handle the fact
                 that the extension of types in the view depends on the
                 state of the relational database, and how to process
                 and optimize queries against the object view. The
                 results are based on experiences from a running
                 prototype implementation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "object views; object-oriented federated databases;
                 query optimization; query processing; relational
                 databases",
}

@Article{Diaz:1997:EEA,
  author =       "Oscar D{\'\i}az and Arturo Jaime",
  title =        "{EXACT}: An Extensible Approach to Active
                 Object-Oriented Databases",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "4",
  pages =        "282--295",
  month =        nov,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:44 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/D=iacute=az:Oscar.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/j/Jaime:Arturo.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006004/70060282.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006004/70060282.pdf",
  abstract =     "Active database management systems (DBMSs) are a
                 fast-growing area of research, mainly due to the large
                 number of applications which can benefit from this
                 active dimension. These applications are far from being
                 homogeneous, requiring different kinds of
                 functionalities. However, most of the active DBMSs
                 described in the literature only provide a {\em fixed,
                 hard-wired\/} execution model to support the active
                 dimension. In object-oriented DBMSs,
                 event-condition-action rules have been proposed for
                 providing active behaviour. This paper presents EXACT,
                 a rule manager for object-oriented DBMSs which provides
                 a variety of options from which the designer can choose
                 the one that best fits the semantics of the concept to
                 be supported by rules. Due to the difficulty of
                 foreseeing future requirements, special attention has
                 been paid to making rule management easily extensible,
                 so that the user can tailor it to suit specific
                 applications. This has been borne out by an
                 implementation in ADAM, an object-oriented DBMS. An
                 example is shown of how the default mechanism can be
                 easily extended to support new requirements.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "active DBMS; extensibility; metaclasses;
                 object-oriented DBMS",
}

@Article{Bohm:1997:SDS,
  author =       "Klemens B{\"o}hm and Karl Aberer and Erich J. Neuhold
                 and Xiaoya Yang",
  title =        "Structured Document Storage and Refined Declarative
                 and Navigational Access Mechanisms in {HyperStorM}",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "4",
  pages =        "296--311",
  month =        nov,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:44 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Aberer:Karl.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/B=ouml=hm:Klemens.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Neuhold:Erich_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Yang:Xiaoya.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006004/70060296.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006004/70060296.pdf",
  abstract =     "The combination of SGML and database technology allows
                 to refine both declarative and navigational access
                 mechanisms for structured document collection: with
                 regard to declarative access, the user can formulate
                 complex information needs without knowing a query
                 language, the respective document type definition (DTD)
                 or the underlying modelling. Navigational access is
                 eased by hyperlink-rendition mechanisms going beyond
                 plain link-integrity checking. With our approach, the
                 database-internal representation of documents is
                 configurable. It allows for an efficient implementation
                 of operations, because DTD knowledge is not needed for
                 document structure recognition. We show how the number
                 of method invocations and the cost of parsing can be
                 significantly reduced.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "document query languages; navigation; OODBMSs; SGML",
}

@Article{Muck:1997:CTH,
  author =       "Thomas A. M{\"u}ck and Martin L. Polaschek",
  title =        "A Configurable Type Hierarchy Index for {OODB}",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "4",
  pages =        "312--332",
  month =        nov,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 08:46:02 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/M=uuml=ck:Thomas_A=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Polaschek:Martin_L=.html",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Mueck:1997:CTH,
  author =       "Thomas A. Mueck and Martin L. Polaschek",
  title =        "A configurable type hierarchy index for {OODB}",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "4",
  pages =        "312--332",
  month =        nov,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:44 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t7006004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/7006004/70060312.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006004/70060312.pdf",
  abstract =     "With respect to the specific requirements of advanced
                 OODB applications, index data structures for type
                 hierarchies in OODBMS have to provide efficient support
                 for multiattribute queries and have to allow index
                 optimization for a particular query profile. We
                 describe the {\em multikey type index\/} and an
                 efficient implementation of this indexing scheme. It
                 meets both requirements: in addition to its
                 multiattribute query capabilities it is designed as a
                 mediator between two standard design alternatives,
                 key-grouping and type-grouping. A prerequisite for the
                 multikey type index is a linearization algorithm which
                 maps type hierarchies to linearly ordered attribute
                 domains in such a way that each subhierarchy is
                 represented by an interval of this domain. The
                 algorithm extends previous results with respect to
                 multiple inheritance. The subsequent evaluation of our
                 proposal focuses on storage space overhead as well as
                 on the number of disk I/O operations needed for query
                 execution. The analytical results for the multikey type
                 index are compared to previously published figures for
                 well-known single-key search structures. The comparison
                 clearly shows the superiority of the multikey type
                 index for a large class of query profiles.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access methods; indexing; multiple inheritance; OODB;
                 type hierarchies",
}

@Article{Berchtold:1997:UEF,
  author =       "Stefan Berchtold and Daniel A. Keim and Hans-Peter
                 Kriegel",
  title =        "Using Extended Feature Objects for Partial Similarity
                 Retrieval",
  journal =      j-VLDB-J,
  volume =       "6",
  number =       "4",
  pages =        "333--348",
  month =        nov,
  year =         "1997",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:44 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb6.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t7006004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Berchtold:Stefan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Keim:Daniel_A=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kriegel:Hans=Peter.html;
                 http://link.springer.de/link/service/journals/00778/bibs/7006004/70060333.htm;
                 http://link.springer.de/link/service/journals/00778/papers/7006004/70060333.pdf",
  abstract =     "In this paper, we introduce the concept of extended
                 feature objects for similarity retrieval. Conventional
                 approaches for similarity search in databases map each
                 object in the database to a point in some
                 high-dimensional feature space and define similarity as
                 some distance measure in this space. For many
                 similarity search problems, this feature-based approach
                 is not sufficient. When retrieving partially similar
                 polygons, for example, the search cannot be restricted
                 to edge sequences, since similar polygon sections may
                 start and end anywhere on the edges of the polygons. In
                 general, inherently continuous problems such as the
                 partial similarity search cannot be solved by using
                 point objects in feature space. In our solution, we
                 therefore introduce extended feature objects consisting
                 of an infinite set of feature points. For an efficient
                 storage and retrieval of the extended feature objects,
                 we determine the minimal bounding boxes of the feature
                 objects in multidimensional space and store these boxes
                 using a spatial access structure. In our concrete
                 polygon problem, sets of polygon sections are mapped to
                 2D feature objects in high-dimensional space which are
                 then approximated by minimal bounding boxes and stored
                 in an R$^*$-tree. The selectivity of the index is
                 improved by using an adaptive decomposition of very
                 large feature objects and a dynamic joining of small
                 feature objects. For the polygon problem, translation,
                 rotation, and scaling invariance is achieved by using
                 the Fourier-transformed curvature of the normalized
                 polygon sections. In contrast to vertex-based
                 algorithms, our algorithm guarantees that no false
                 dismissals may occur and additionally provides fast
                 search times for realistic database sizes. We evaluate
                 our method using real polygon data of a supplier for
                 the car manufacturing industry.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "CAD databases; Fourier transformation; indexing and
                 query processing of spatial objects; partial similarity
                 retrieval",
}

@Article{Han:1998:ORQ,
  author =       "Jia Liang Han",
  title =        "Optimizing Relational Queries in Connection
                 Hypergraphs: Nested Queries, Views, and Binding
                 Propagations",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "1",
  pages =        "1--11",
  month =        feb,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Han:Jia_Liang.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007001/80070001.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007001/80070001.pdf",
  abstract =     "We optimize relational queries using connection
                 hypergraphs (CHGs). All operations including
                 value-passing between SQL blocks can be set-oriented.
                 By introducing partial evaluations, reordering
                 operations can be achieved for nested queries. For a
                 query using views, we merge CHGs for the views and the
                 query into one CHG and then apply query optimization.
                 Furthermore, we may simulate magic sets methods
                 elegantly in a CHG. Sideways information-passing
                 strategies (SIPS) in a CHG amount to partial
                 evaluations of SIPS paths. We introduce the maximum
                 SIPS strategy, which performs SIPS for all bindings and
                 all SIPS paths for a query. The new method has several
                 advantages. First, the maximum SIPS strategy can be
                 more efficient than the previous SIPS based on simple
                 heuristics. Second, it is conceptually simple and easy
                 to implement. Third, the processing strategies may be
                 incorporated with the search space for query execution
                 plans, which is a proven optimization strategy
                 introduced by System R. Fourth, it provides a general
                 framework of query optimization and may potentially be
                 used to optimize next-generation database systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "connection hypergraphs; partial evaluations;
                 relational query optimization; search space; SIPS",
}

@Article{Hanson:1998:FRC,
  author =       "Eric N. Hanson and I.-Cheng Chen and Roxana Dastur and
                 Kurt Engel and Vijay Ramaswamy and Wendy Tan and Chun
                 Xu",
  title =        "A Flexible and Recoverable Client\slash Server
                 Database Event Notification System",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "1",
  pages =        "12--24",
  month =        feb,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chen:I==Cheng.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Dastur:Roxana.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/e/Engel:Kurt.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Hanson:Eric_N=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ramaswamy:Vijay.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tan:Wendy.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/x/Xu:Chun.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007001/80070012.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007001/80070012.pdf",
  abstract =     "A software architecture is presented that allows
                 client application programs to interact with a DBMS
                 server in a flexible and powerful way, using either
                 direct, volatile messages, or messages sent via
                 recoverable queues. Normal requests from clients to the
                 server and replies from the server to clients can be
                 transmitted using direct or recoverable messages. In
                 addition, an application event notification mechanism
                 is provided, whereby client applications running
                 anywhere on the network can register for events, and
                 when those events are raised, the clients are notified.
                 A novel parameter passing mechanism allows a set of
                 tuples to be included in an event notification. The
                 event mechanism is particularly useful in an active
                 DBMS, where events can be raised by triggers to signal
                 running application programs.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Mehta:1998:OPM,
  author =       "Ashish Mehta and James Geller and Yehoshua Perl and
                 Erich J. Neuhold",
  title =        "The {OODB} Path-Method Generator ({PMG}) Using Access
                 Weights and Precomputed Access Relevance",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "1",
  pages =        "25--47",
  month =        feb,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Geller:James.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mehta:Ashish.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Neuhold:Erich_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Perl:Yehoshua.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007001/80070025.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007001/80070025.pdf",
  abstract =     "A {\em path-method\/} is used as a mechanism in
                 object-oriented databases (OODBs) to retrieve or to
                 update information relevant to one class that is not
                 stored with that class but with some other class. A
                 path-method is a method which traverses from one class
                 through a chain of connections between classes and
                 accesses information at another class. However, it is a
                 difficult task for a casual user or even an application
                 programmer to write path-methods to facilitate queries.
                 This is because it might require comprehensive
                 knowledge of many classes of the conceptual schema that
                 are not directly involved in the query, and therefore
                 may not even be included in a user's (incomplete) view
                 about the contents of the database. We have developed a
                 system, called {\em path-method generator\/} (PMG),
                 which generates path-methods automatically according to
                 a user's database-manipulating requests. The PMG offers
                 the user one of the possible path-methods and the user
                 verifies from his knowledge of the intended purpose of
                 the request whether that path-method is the desired
                 one. If the path method is rejected, then the user can
                 utilize his now increased knowledge about the database
                 to request (with additional parameters given) another
                 offer from the PMG. The PMG is based on {\em access
                 weights\/} attached to the connections between classes
                 and precomputed {\em access relevance\/} between every
                 pair of classes of the OODB. Specific rules for access
                 weight assignment and algorithms for computing access
                 relevance appeared in our previous papers [MGPF92,
                 MGPF93, MGPF96]. In this paper, we present a variety of
                 traversal algorithms based on access weights and
                 precomputed access relevance. Experiments identify some
                 of these algorithms as very successful in generating
                 most desired path-methods. The PMG system utilizes
                 these successful algorithms and is thus an efficient
                 tool for aiding the user with the difficult task of
                 querying and updating a large OODB.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access relevance; access weight; object-oriented
                 databases; OODB queries; path-method; traversal
                 algorithms",
}

@Article{Scheuermann:1998:DPL,
  author =       "Peter Scheuermann and Gerhard Weikum and Peter
                 Zabback",
  title =        "Data Partitioning and Load Balancing in Parallel Disk
                 Systems",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "1",
  pages =        "48--66",
  month =        feb,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Scheuermann:Peter.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Weikum:Gerhard.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Zabback:Peter.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007001/80070048.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007001/80070048.pdf",
  abstract =     "Parallel disk systems provide opportunities for
                 exploiting I/O parallelism in two possible ways, namely
                 via inter-request and intra-request parallelism. In
                 this paper, we discuss the main issues in performance
                 tuning of such systems, namely striping and load
                 balancing, and show their relationship to response time
                 and throughput. We outline the main components of an
                 intelligent, self-reliant file system that aims to
                 optimize striping by taking into account the
                 requirements of the applications, and performs load
                 balancing by judicious file allocation and dynamic
                 redistributions of the data when access patterns
                 change. Our system uses simple but effective heuristics
                 that incur only little overhead. We present performance
                 experiments based on synthetic workloads and real-life
                 traces.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data allocation; disk cooling; file striping; load
                 balancing; parallel disk systems; performance tuning",
}

@Article{Ishakbeyoglu:1998:MII,
  author =       "Naci S. Ishakbeyo{\u{g}}lu and Z. Meral
                 {\"O}zsoyo{\u{g}}lu",
  title =        "Maintenance of Implication Integrity Constraints Under
                 Updates to Constraints",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "2",
  pages =        "67--78",
  month =        may,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/=/=Ouml=zsoyoglu:Z=_Meral.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/i/Ishakbeyoglu:Naci.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007002/80070067.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007002/80070067.pdf",
  abstract =     "Semantic integrity constraints are used for enforcing
                 the integrity of the database as well as for improving
                 the efficiency of the database utilization. Although
                 semantic integrity constraints are usually much more
                 static as compared to the data itself, changes in the
                 data semantics may necessitate corresponding changes in
                 the constraint base. In this paper we address the
                 problems related with maintaining a consistent and
                 non-redundant set of constraints satisfied by the
                 database in the case of updates to the constraint base.
                 We consider implication constraints as semantic
                 integrity constraints. The constraints are represented
                 as conjunctions of inequalities. We present a
                 methodology to determine whether a constraint is
                 redundant or contradictory with respect to a set of
                 constraints. The methodology is based on the
                 partitioning of the constraint base which improves the
                 efficiency of algorithms that check whether a
                 constraint is redundant or contradictory with respect
                 to a constraint base.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "implication integrity constraints; integrity
                 constraints; partitioning; redundancy; satisfiability",
}

@Article{Dessloch:1998:ADP,
  author =       "Stefan De{\ss}loch and Theo H{\"a}rder and Nelson
                 Mendon{\c{c}}a Mattos and Bernhard Mitschang and
                 Joachim Thomas",
  title =        "Advanced Data Processing in {KRISYS}: Modeling
                 Concepts, Implementation Techniques, and Client\slash
                 Server Issues",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "2",
  pages =        "79--95",
  month =        may,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/De=szlig=loch:Stefan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/H=auml=rder:Theo.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mattos:Nelson_Mendon=ccedil=a.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mitschang:Bernhard.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Thomas:Joachim.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007002/80070079.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007002/80070079.pdf",
  abstract =     "The increasing power of modern computers is steadily
                 opening up new application domains for advanced data
                 processing such as engineering and knowledge-based
                 applications. To meet their requirements, concepts for
                 advanced data management have been investigated during
                 the last decade, especially in the field of object
                 orientation. Over the last couple of years, the
                 database group at the University of Kaiserslautern has
                 been developing such an advanced database system, the
                 KRISYS prototype. In this article, we report on the
                 results and experiences obtained in the course of this
                 project. The primary objective for the first version of
                 KRISYS was to provide semantic features, such as an
                 expressive data model, a set-oriented query language,
                 deductive as well as active capabilities. The first
                 KRISYS prototype became completely operational in 1989.
                 To evaluate its features and to stabilize its
                 functionality, we started to develop several
                 applications with the system. These experiences marked
                 the starting point for an overall redesign of KRISYS.
                 Major goals were to tune KRISYS and its
                 query-processing facilities to a suitable client/server
                 environment, as well as to provide elaborate mechanisms
                 for consistency control comprising semantic integrity
                 constraints, multi-user synchronization, and failure
                 recovery. The essential aspects of the resulting
                 client/server architecture are embodied by the
                 client-side data management needed to effectively
                 support advanced applications and to gain the required
                 system performance for interactive work. The project
                 stages of KRISYS properly reflect the essential
                 developments that have taken place in the research on
                 advanced database systems over the last years. Hence,
                 the subsequent discussions will bring up a number of
                 important aspects with regard to advanced data
                 processing that are of significant general importance,
                 as well as of general applicability to database
                 systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "client\slash server architectures; Consistency
                 control; object-oriented modeling concepts; query
                 processing; run-time optimization",
}

@Article{Abiteboul:1998:LVS,
  author =       "Serge Abiteboul and Sophie Cluet and Tova Milo",
  title =        "A Logical View of Structured Files",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "2",
  pages =        "96--114",
  month =        may,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Abiteboul:Serge.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Cluet:Sophie.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Milo:Tova.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007002/80070096.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007002/80070096.pdf",
  abstract =     "Structured data stored in files can benefit from
                 standard database technology. In particular, we show
                 here how such data can be queried and updated using
                 declarative database languages. We introduce the notion
                 of {\em structuring schema}, which consists of a
                 grammar annotated with database programs. Based on a
                 structuring schema, a file can be viewed as a database
                 structure, queried and updated as such. For {\em
                 queries}, we show that almost standard database
                 optimization techniques can be used to answer queries
                 without having to construct the entire database. For
                 {\em updates}, we study in depth the propagation to the
                 file of an update specified on the database view of
                 this file. The problem is not feasible in general and
                 we present a number of negative results. The positive
                 results consist of techniques that allow to propagate
                 updates efficiently under some reasonable {\em
                 locality\/} conditions on the structuring schemas.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database; file system; query; query and update
                 optimization; textual data; update",
}

@Article{Ooi:1998:FIR,
  author =       "Beng Chin Ooi and Kian-Lee Tan and Tat Seng Chua and
                 Wynne Hsu",
  title =        "Fast Image Retrieval Using Color-Spatial Information",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "2",
  pages =        "115--128",
  month =        may,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:45 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chua:Tat=Seng.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Hsu:Wynne.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/o/Ooi:Beng_Chin.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tan:Kian=Lee.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007002/80070115.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007002/80070115.pdf",
  abstract =     "In this paper, we present an image retrieval system
                 that employs both the color and spatial information of
                 images to facilitate the retrieval process. The basic
                 unit used in our technique is a {\em single-colored
                 cluster}, which bounds a homogeneous region of that
                 color in an image. Two clusters from two images are
                 similar if they are of the same color and overlap in
                 the image space. The number of clusters that can be
                 extracted from an image can be very large, and it
                 affects the accuracy of retrieval. We study the effect
                 of the number of clusters on retrieval effectiveness to
                 determine an appropriate value for ``optimal''
                 performance. To facilitate efficient retrieval, we also
                 propose a multi-tier indexing mechanism called the {\em
                 Sequenced Multi-Attribute Tree\/} (SMAT). We
                 implemented a two-tier SMAT, where the first layer is
                 used to prune away clusters that are of different
                 colors, while the second layer discriminates clusters
                 of different spatial locality. We conducted an
                 experimental study on an image database consisting of
                 12,000 images. Our results show the effectiveness of
                 the proposed color-spatial approach, and the efficiency
                 of the proposed indexing mechanism.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "color-spatial information; content-based retrieval;
                 sequenced multi-attribute tree; single-colored
                 cluster",
}

@Article{Jarke:1998:GE,
  author =       "Matthias Jarke",
  title =        "Guest {Editorial}",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "3",
  pages =        "129--129",
  month =        aug,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:47 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t8007003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/8007003/80070129.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007003/80070129.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Seshadri:1998:EAD,
  author =       "Praveen Seshadri",
  title =        "Enhanced Abstract Data Types in Object-Relational
                 Databases",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "3",
  pages =        "130--140",
  month =        aug,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:47 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Special Issue on {VLDB 1997}. Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Seshadri:Praveen.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007003/80070130.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007003/80070130.pdf",
  abstract =     "The explosion in complex multimedia content makes it
                 crucial for database systems to support such data
                 efficiently. This paper argues that the ``blackbox''
                 ADTs used in current object-relational systems inhibit
                 their performance, thereby limiting their use in
                 emerging applications. Instead, the next generation of
                 object-relational database systems should be based on
                 enhanced abstract data type (E-ADT) technology. An
                 (E-ADT) can expose the {\em semantics\/} of its methods
                 to the database system, thereby permitting advanced
                 query optimizations. Fundamental architectural changes
                 are required to build a database system with E-ADTs;
                 the added functionality should not compromise the
                 modularity of data types and the extensibility of the
                 type system. The implementation issues have been
                 explored through the development of E-ADTs in {\em
                 Predator}. Initial performance results demonstrate an
                 order of magnitude in performance improvements.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database types; extensibility; object-relational
                 database; query optimization",
}

@Article{Kraiss:1998:IDC,
  author =       "Achim Kraiss and Gerhard Weikum",
  title =        "Integrated Document Caching and Prefetching in Storage
                 Hierarchies Based on {Markov}-Chain Predictions",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "3",
  pages =        "141--162",
  month =        aug,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:47 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kraiss:Achim.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Weikum:Gerhard.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007003/80070141.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007003/80070141.pdf",
  abstract =     "Large multimedia document archives may hold a major
                 fraction of their data in tertiary storage libraries
                 for cost reasons. This paper develops an integrated
                 approach to the vertical data migration between the
                 tertiary, secondary, and primary storage in that it
                 reconciles speculative prefetching, to mask the high
                 latency of the tertiary storage, with the replacement
                 policy of the document caches at the secondary and
                 primary storage level, and also considers the
                 interaction of these policies with the tertiary and
                 secondary storage request scheduling. The integrated
                 migration policy is based on a continuous-time Markov
                 chain model for predicting the expected number of
                 accesses to a document within a specified time horizon.
                 Prefetching is initiated only if that expectation is
                 higher than those of the documents that need to be
                 dropped from secondary storage to free up the necessary
                 space. In addition, the possible resource contention at
                 the tertiary and secondary storage is taken into
                 account by dynamically assessing the response-time
                 benefit of prefetching a document versus the penalty
                 that it would incur on the response time of the pending
                 document requests. The parameters of the
                 continuous-time Markov chain model, the probabilities
                 of co-accessing certain documents and the interaction
                 times between successive accesses, are dynamically
                 estimated and adjusted to evolving workload patterns by
                 keeping online statistics. The integrated policy for
                 vertical data migration has been implemented in a
                 prototype system. The system makes profitable use of
                 the Markov chain model also for the scheduling of
                 volume exchanges in the tertiary storage library.
                 Detailed simulation experiments with Web-server-like
                 synthetic workloads indicate significant gains in terms
                 of client response time. The experiments also show that
                 the overhead of the statistical bookkeeping and the
                 computations for the access predictions is
                 affordable.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "caching; Markov chains; performance; prefetching;
                 scheduling; stochastic modeling; tertiary storage",
}

@Article{Chakrabarti:1998:SFS,
  author =       "Soumen Chakrabarti and Byron Dom and Rakesh Agrawal
                 and Prabhakar Raghavan",
  title =        "Scalable Feature Selection, Classification and
                 Signature Generation for Organizing Large Text
                 Databases into Hierarchical Topic Taxonomies",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "3",
  pages =        "163--178",
  month =        aug,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:47 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Agrawal:Rakesh.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chakrabarti:Soumen.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Dom:Byron.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Raghavan:Prabhakar.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007003/80070163.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007003/80070163.pdf",
  abstract =     "We explore how to organize large text databases
                 hierarchically by topic to aid better searching,
                 browsing and filtering. Many corpora, such as Internet
                 directories, digital libraries, and patent databases
                 are manually organized into topic hierarchies, also
                 called {\em taxonomies}. Similar to indices for
                 relational data, taxonomies make search and access more
                 efficient. However, the exponential growth in the
                 volume of on-line textual information makes it nearly
                 impossible to maintain such taxonomic organization for
                 large, fast-changing corpora by hand. We describe an
                 automatic system that starts with a small sample of the
                 corpus in which topics have been assigned by hand, and
                 then updates the database with new documents as the
                 corpus grows, assigning topics to these new documents
                 with high speed and accuracy. To do this, we use
                 techniques from statistical pattern recognition to
                 efficiently separate the {\em feature\/} words, or {\em
                 discriminants}, from the {\em noise\/} words at each
                 node of the taxonomy. Using these, we build a
                 multilevel classifier. At each node, this classifier
                 can ignore the large number of ``noise'' words in a
                 document. Thus, the classifier has a small model size
                 and is very fast. Owing to the use of context-sensitive
                 features, the classifier is very accurate. As a
                 by-product, we can compute for each document a set of
                 terms that occur significantly more often in it than in
                 the classes to which it belongs. We describe the design
                 and implementation of our system, stressing how to
                 exploit standard, efficient relational operations like
                 sorts and joins. We report on experiences with the
                 Reuters newswire benchmark, the US patent database, and
                 web document samples from Yahoo!. We discuss
                 applications where our system can improve searching and
                 filtering capabilities.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Roy:1998:GCO,
  author =       "Prasan Roy and S. Seshadri and Abraham Silberschatz
                 and S. Sudarshan and S. Ashwin",
  title =        "Garbage Collection in Object-Oriented Databases Using
                 Transactional Cyclic Reference Counting",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "3",
  pages =        "179--193",
  month =        aug,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:47 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Ashwin:S=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Roy:Prasan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Seshadri:S=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Silberschatz:Abraham.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sudarshan:S=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007003/80070179.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007003/80070179.pdf",
  abstract =     "Garbage collection is important in object-oriented
                 databases to free the programmer from explicitly
                 deallocating memory. In this paper, we present a
                 garbage collection algorithm, called Transactional
                 Cyclic Reference Counting (TCRC), for object-oriented
                 databases. The algorithm is based on a variant of a
                 reference-counting algorithm proposed for functional
                 programming languages The algorithm keeps track of
                 auxiliary reference count information to detect and
                 collect cyclic garbage. The algorithm works correctly
                 in the presence of concurrently running transactions,
                 and system failures. It does not obtain any long-term
                 locks, thereby minimizing interference with transaction
                 processing. It uses recovery subsystem logs to detect
                 pointer updates; thus, existing code need not be
                 rewritten. Finally, it exploits schema information, if
                 available, to reduce costs. We have implemented the
                 TCRC algorithm and present results of a performance
                 study of the implementation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Ng:1998:IRM,
  author =       "Wee Teck Ng and Peter M. Chen",
  title =        "Integrating Reliable Memory in Databases",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "3",
  pages =        "194--204",
  month =        aug,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:47 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chen:Peter_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Ng:Wee_Teck.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007003/80070194.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007003/80070194.pdf",
  abstract =     "Recent results in the Rio project at the University of
                 Michigan show that it is possible to create an area of
                 main memory that is as safe as disk from operating
                 system crashes. This paper explores how to integrate
                 the reliable memory provided by the Rio file cache into
                 a database system. Prior studies have analyzed the
                 performance benefits of reliable memory; we focus
                 instead on how different designs affect reliability. We
                 propose three designs for integrating reliable memory
                 into databases: non-persistent database buffer cache,
                 persistent database buffer cache, and persistent
                 database buffer cache with protection. Non-persistent
                 buffer caches use an I/O interface to reliable memory
                 and require the fewest modifications to existing
                 databases. However, they waste memory capacity and
                 bandwidth due to double buffering. Persistent buffer
                 caches use a memory interface to reliable memory by
                 mapping it into the database address space. This places
                 reliable memory under complete database control and
                 eliminates double buffering, but it may expose the
                 buffer cache to database errors. Our third design
                 reduces this exposure by write protecting the buffer
                 pages. Extensive fault tests show that mapping reliable
                 memory into the database address space does not
                 significantly hurt reliability. This is because wild
                 stores rarely touch dirty, committed pages written by
                 previous transactions. As a result, we believe that
                 databases should use a memory interface to reliable
                 memory.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "main memory database system (MMDB); recovery;
                 reliability",
}

@Article{Ozsu:1998:I,
  author =       "M. Tamer {\"O}zsu and Stavros Christodoulakis",
  title =        "Introduction",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "205--205",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:48 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Ozsu:1998:SIM,
  author =       "M. Tamer {\"O}zsu and Stavros Christodoulakis",
  title =        "Special Issue on Multimedia Databases: Introduction",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "205--205",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 10:11:57 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007004.htm;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/=/=Ouml=zsu:M=_Tamer.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Christodoulakis:Stavros.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007004/80070205.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007004/80070205.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Garofalakis:1998:PRS,
  author =       "Minos N. Garofalakis and Banu {\"O}zden and Avi
                 Silberschatz",
  title =        "On Periodic Resource scheduling for Continuous-Media
                 Databases",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "206--225",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 10:11:57 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007004.htm;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/=/=Ouml=zden:Banu.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Garofalakis:Minos_N=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Silberschatz:Abraham.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007004/80070206.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007004/80070206.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  xxauthor =     "Minos N. Garofalakis and Banu {\"O}zden and Abraham
                 Silberschatz",
}

@Article{Jiang:1998:STC,
  author =       "Haitao Jiang and Ahmed K. Elmagarmid",
  title =        "Spatial and Temporal Content-Based Access to
                 Hypervideo Databases",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "226--238",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:48 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/e/Elmagarmid:Ahmed_K=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/j/Jiang:Haitao.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007004/80070226.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007004/80070226.pdf",
  abstract =     "Providing content-based video query, retrieval and
                 browsing is the most important goal of a video database
                 management system (VDBMS). Video data is unique not
                 only in terms of its spatial and temporal
                 characteristics, but also in the semantic associations
                 manifested by the entities present in the video. This
                 paper introduces a novel video data model called {\em
                 Logical Hypervideo Data Model}. In addition to
                 multilevel video abstractions, the model is capable of
                 representing video entities that users are interested
                 in (defined as {\em hot objects\/}) and their semantic
                 associations with other logical video abstractions,
                 including hot objects themselves. The semantic
                 associations are modeled as {\em video hyperlinks\/}
                 and video data with such property are called {\em
                 hypervideo}. Video hyperlinks provide a flexible and
                 effective way of browsing video data. Based on the
                 proposed model, video queries can be specified with
                 both temporal and spatial constraints, as well as with
                 semantic descriptions of the video data. The
                 characteristics of hot objects' spatial and temporal
                 relations and efficient evaluation of them are also
                 discussed. Some query examples are given to demonstrate
                 the expressiveness of the video data model and query
                 language. Finally, we describe a modular video database
                 system architecture that our web-based prototype is
                 based on.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "content-based query; hot object; hypervideo; spatial
                 and temporal constraint; video database",
}

@Article{Ng:1998:OCO,
  author =       "Raymond T. Ng and Paul Shum",
  title =        "Optimal Clip Ordering for Multi-Clip Queries",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "239--252",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:48 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Ng:Raymond_T=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Shum:Paul.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007004/80070239.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007004/80070239.pdf",
  abstract =     "A multi-clip query requests multiple video clips be
                 returned as the answer of the query. In many
                 applications and situations, the order in which these
                 clips are to be delivered does not matter that much to
                 the user. This allows the system ample opportunities to
                 optimize system throughput by using schedules that
                 maximize the effect of piggybacking. In this paper, we
                 study how to find such optimal schedules. In
                 particular, we consider two optimization criteria: (i)
                 one based on maximizing the number of piggybacked
                 clips, and (ii) the other based on maximizing the
                 impact on buffer space. We show that the optimal
                 schedule under the first criterion is equivalent to a
                 maximum matching in a suitably defined bipartite graph,
                 and that under the second criterion, the optimal
                 schedule is equivalent to a maximum matching in a
                 suitably defined weighted bipartite graph. Our
                 experimental results, which are based on realistic
                 distributions, indicate that both kinds of optimal
                 schedules can lead to a gain in throughput of over
                 300\%. And yet the time taken to compute such an
                 optimal schedule is negligible. Finally, we show how to
                 deal with clips that are variable in length.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "admission control; bipartite graph matching;
                 performance of multimedia systems",
}

@Article{Soffer:1998:ISI,
  author =       "Aya Soffer and Hanan Samet",
  title =        "Integrating Symbolic Images into a Multimedia Database
                 System Using Classification and Abstraction
                 Approaches",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "253--274",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:48 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Samet:Hanan.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Soffer:Aya.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007004/80070253.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007004/80070253.pdf",
  abstract =     "Symbolic images are composed of a finite set of
                 symbols that have a semantic meaning. Examples of
                 symbolic images include maps (where the semantic
                 meaning of the symbols is given in the legend),
                 engineering drawings, and floor plans. Two approaches
                 for supporting queries on symbolic-image databases that
                 are based on image content are studied. The
                 classification approach preprocesses all symbolic
                 images and attaches a semantic classification and an
                 associated certainty factor to each object that it
                 finds in the image. The abstraction approach describes
                 each object in the symbolic image by using a vector
                 consisting of the values of some of its features (e.g.,
                 shape, genus, etc.). The approaches differ in the way
                 in which responses to queries are computed. In the
                 classification approach, images are retrieved on the
                 basis of whether or not they contain objects that have
                 the same classification as the objects in the query. On
                 the other hand, in the abstraction approach, retrieval
                 is on the basis of similarity of feature vector values
                 of these objects. Methods of integrating these two
                 approaches into a relational multimedia database
                 management system so that symbolic images can be stored
                 and retrieved based on their content are described.
                 Schema definitions and indices that support query
                 specifications involving spatial as well as contextual
                 constraints are presented. Spatial constraints may be
                 based on both locational information (e.g., distance)
                 and relational information (e.g., north of). Different
                 strategies for image retrieval for a number of typical
                 queries using these approaches are described. Estimated
                 costs are derived for these strategies. Results are
                 reported of a comparative study of the two approaches
                 in terms of image insertion time, storage space,
                 retrieval accuracy, and retrieval time.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "image indexing; multimedia databases; query
                 optimization; retrieval by content; spatial databases;
                 symbolic-image databases",
}

@Article{Zezula:1998:ASR,
  author =       "Pavel Zezula and Pasquale Savino and Giuseppe Amato
                 and Fausto Rabitti",
  title =        "Approximate Similarity Retrieval with {M}-Trees",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "275--293",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:48 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Amato:Giuseppe.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Rabitti:Fausto.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Savino:Pasquale.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Zezula:Pavel.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007004/80070275.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007004/80070275.pdf",
  abstract =     "Motivated by the urgent need to improve the efficiency
                 of similarity queries, approximate similarity retrieval
                 is investigated in the environment of a metric tree
                 index called the M-tree. Three different approximation
                 techniques are proposed, which show how to forsake
                 query precision for improved performance. Measures are
                 defined that can quantify the improvements in
                 performance efficiency and the quality of
                 approximations. The proposed approximation techniques
                 are then tested on various synthetic and real-life
                 files. The evidence obtained from the experiments
                 confirms our hypothesis that a high-quality
                 approximated similarity search can be performed at a
                 much lower cost than that needed to obtain the exact
                 results. The proposed approximation techniques are
                 scalable and appear to be independent of the metric
                 used. Extensions of these techniques to the
                 environments of other similarity search indexes are
                 also discussed.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access structures; approximation algorithms; distance
                 only data; performance evaluation; similarity search",
}

@Article{Balkir:1998:DPM,
  author =       "Nevzat Hurkan Balkir and Gultekin {\"O}zsoyoglu",
  title =        "Delivering Presentations from Multimedia Servers",
  journal =      j-VLDB-J,
  volume =       "7",
  number =       "4",
  pages =        "294--307",
  month =        dec,
  year =         "1998",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:48 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb7.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t8007004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/=/=Ouml=zsoyoglu:Gultekin.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Balkir:Nevzat_Hurkan.html;
                 http://link.springer.de/link/service/journals/00778/bibs/8007004/80070294.htm;
                 http://link.springer.de/link/service/journals/00778/papers/8007004/80070294.pdf",
  abstract =     "Most multimedia servers reported in the literature are
                 designed to serve multiple and independent video/audio
                 streams. We think that, in future, multimedia servers
                 will also serve complete presentations. Multimedia
                 presentations provide unique opportunities to develop
                 algorithms for buffer management and admission control,
                 as execution-time consumption requirements of
                 presentations are known a priori. In this paper, we
                 examine presentations in three different domains
                 (heavyweight, middleweight, and lightweight) and
                 provide buffer management and admission control
                 algorithms for the three domains. We propose two
                 improvements (flattening and dynamic-adjustments) on
                 the schedules created for the heavyweight
                 presentations. Results from a simulation environment
                 are presented.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "admission control; buffer management; flattening;
                 multimedia presentations",
}

@Article{Li:1999:FJU,
  author =       "Zhe Li and Kenneth A. Ross",
  title =        "Fast Joins Using Join Indices",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "1",
  pages =        "1--24",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:49 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Li:Zhe.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Ross:Kenneth_A=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008001/90080001.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008001/90080001.pdf",
  abstract =     "Two new algorithms, ``Jive join'' and ``Slam join,''
                 are proposed for computing the join of two relations
                 using a join index. The algorithms are duals: Jive join
                 range-partitions input relation tuple ids and then
                 processes each partition, while Slam join forms ordered
                 runs of input relation tuple ids and then merges the
                 results. Both algorithms make a single sequential pass
                 through each input relation, in addition to one pass
                 through the join index and two passes through a
                 temporary file, whose size is half that of the join
                 index. Both algorithms require only that the number of
                 blocks in main memory is of the order of the square
                 root of the number of blocks in the smaller relation.
                 By storing intermediate and final join results in a
                 vertically partitioned fashion, our algorithms need to
                 manipulate less data in memory at a given time than
                 other algorithms. The algorithms are resistant to data
                 skew and adaptive to memory fluctuations. Selection
                 conditions can be incorporated into the algorithms.
                 Using a detailed cost model, the algorithms are
                 analyzed and compared with competing algorithms. For
                 large input relations, our algorithms perform
                 significantly better than Valduriez's algorithm, the
                 TID join algorithm, and hash join algorithms. An
                 experimental study is also conducted to validate the
                 analytical results and to demonstrate the performance
                 characteristics of each algorithm in practice.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "decision support systems; query processing",
  remark =       "Check month: April or May??",
}

@Article{Harder:1999:IPS,
  author =       "Theo H{\"a}rder and G{\"u}nter Sauter and Joachim
                 Thomas",
  title =        "The Intrinsic Problems of Structural Heterogeneity and
                 an Approach to Their Solution",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "1",
  pages =        "25--43",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:49 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/H=auml=rder:Theo.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sauter:G=uuml=nter.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Thomas:Joachim.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008001/90080025.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008001/90080025.pdf",
  abstract =     "This paper focuses on the problems that arise when
                 integrating data from heterogeneous sources in a
                 single, unified database view. At first, we give a
                 detailed analysis of the kinds of structural
                 heterogeneity that occur when unified views are derived
                 from different database systems. We present the results
                 in a multiple tier architecture which distinguishes
                 different levels of heterogeneity and relates them to
                 their underlying causes as well as to the mapping
                 conflicts resulting from the view derivation process.
                 As the second essential contribution, the paper
                 presents our approach to a mapping language solving the
                 identified conflicts. The main characteristics of the
                 language are its descriptiveness, its capability to map
                 between schemas written in the relational,
                 object-oriented, ER, or EXPRESS data model, and its
                 facilities for specifying user-defined update
                 operations on the view that are to be propagated to the
                 data sources. Finally, we briefly discuss how this
                 mapping information is employed to convert queries
                 formulated with respect to the integrated view, into
                 database operations over the heterogeneous data
                 sources.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "heterogeneity; legacy systems; mapping language;
                 schema integration; schema mapping; updatable views",
  remark =       "Check month: April or May??",
}

@Article{Huang:1999:CTP,
  author =       "Yueh-Min Huang and Jen-Wen Ding and Shiao-Li Tsao",
  title =        "Constant Time Permutation: An Efficient Block
                 Allocation Strategy for Variable-Bit-Rate Continuous
                 Media Data",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "1",
  pages =        "44--54",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:49 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/Ding:Jen=Wen.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Huang:Yueh=Min.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tsao:Shiao=Li.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008001/90080044.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008001/90080044.pdf",
  abstract =     "To provide high accessibility of continuous-media (CM)
                 data, CM servers generally stripe data across multiple
                 disks. Currently, the most widely used striping scheme
                 for CM data is round-robin permutation (RRP).
                 Unfortunately, when RRP is applied to variable-bit-rate
                 (VBR) CM data, load imbalance across multiple disks
                 occurs, thereby reducing overall system performance. In
                 this paper, the performance of a VBR CM server with RRP
                 is analyzed. In addition, we propose an efficient
                 striping scheme called constant time permutation (CTP),
                 which takes the VBR characteristic into account and
                 obtains a more balanced load than RRP. Analytic models
                 of both RRP and CTP are presented, and the models are
                 verified via trace-driven simulations. Analysis and
                 simulation results show that CTP can substantially
                 increase the number of clients supported, though it
                 might introduce a few seconds/minutes of initial
                 delay.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "continuous-media server; data placement; load
                 balancing; striping; video-on-demand (VOD)",
  remark =       "Check month: April or May??",
}

@Article{Kabra:1999:OOO,
  author =       "Navin Kabra and David J. DeWitt",
  title =        "{OPT}++ : an object-oriented implementation for
                 extensible database query optimization",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "1",
  pages =        "55--78",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:49 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/d/DeWitt:David_J=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kabra:Navin.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008001/90080055.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008001/90080055.pdf",
  abstract =     "In this paper we describe the design and
                 implementation of OPT++, a tool for extensible database
                 query optimization that uses an object-oriented design
                 to simplify the task of implementing, extending, and
                 modifying an optimizer. Building an optimizer using
                 OPT++ makes it easy to extend the query algebra (to add
                 new query algebra operators and physical implementation
                 algorithms to the system), easy to change the search
                 space, and also to change the search strategy.
                 Furthermore, OPT++ comes equipped with a number of
                 search strategies that are available for use by an
                 optimizer-implementor. OPT++ considerably simplifies
                 both, the task of implementing an optimizer for a new
                 database system, and the task of evaluating alternative
                 optimization techniques and strategies to decide what
                 techniques are best suited for that database system. We
                 present the results of a series of performance studies.
                 These results validate our design and show that, in
                 spite of its flexibility, OPT++ can be used to build
                 efficient optimizers.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "extensibility; object-relational databases; query
                 optimization; software architecture",
  remark =       "Check month: April or May??",
}

@Article{Krivokapic:1999:DDD,
  author =       "Natalija Krivokapi{\'c} and Alfons Kemper and Ehud
                 Gudes",
  title =        "Deadlock Detection in Distributed Database Systems:
                 {A} New Algorithm and a Comparative Performance
                 Analysis",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "2",
  pages =        "79--100",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:50 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Gudes:Ehud.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kemper:Alfons.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Krivokapic:Natalija.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008002/90080079.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008002/90080079.pdf",
  abstract =     "This paper attempts a comprehensive study of deadlock
                 detection in distributed database systems. First, the
                 two predominant deadlock models in these systems and
                 the four different distributed deadlock detection
                 approaches are discussed. Afterwards, a new deadlock
                 detection algorithm is presented. The algorithm is
                 based on dynamically creating {\em deadlock detection
                 agents\/} (DDAs), each being responsible for detecting
                 deadlocks in one connected component of the global
                 wait-for-graph (WFG). The DDA scheme is a
                 ``self-tuning'' system: after an initial warm-up phase,
                 dedicated DDAs will be formed for ``centers of
                 locality'', i.e., parts of the system where many
                 conflicts occur. A dynamic shift in locality of the
                 distributed system will be responded to by
                 automatically creating new DDAs while the obsolete ones
                 terminate. In this paper, we also compare the most
                 competitive representative of each class of algorithms
                 suitable for distributed database systems based on a
                 simulation model, and point out their relative
                 strengths and weaknesses. The extensive experiments we
                 carried out indicate that our newly proposed deadlock
                 detection algorithm outperforms the other algorithms in
                 the vast majority of configurations and workloads and,
                 in contrast to all other algorithms, is very robust
                 with respect to differing load and access profiles.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "comparative performance analysis; deadlock detection;
                 distributed database systems; simulation study",
  remark =       "Check month: April or May??",
}

@Article{Boncz:1999:MPQ,
  author =       "Peter A. Boncz and Martin L. Kersten",
  title =        "{MIL} primitives for querying a fragmented world",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "2",
  pages =        "101--119",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:50 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Boncz:Peter_A=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kersten:Martin_L=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008002/90080101.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008002/90080101.pdf",
  abstract =     "In query-intensive database application areas, like
                 decision support and data mining, systems that use
                 vertical fragmentation have a significant performance
                 advantage. In order to support relational or object
                 oriented applications on top of such a fragmented data
                 model, a flexible yet powerful intermediate language is
                 needed. This problem has been successfully tackled in
                 Monet, a modern extensible database kernel developed by
                 our group. We focus on the design choices made in the
                 Monet interpreter language (MIL), its algebraic query
                 language, and outline how its concept of tactical
                 optimization enhances and simplifies the optimization
                 of complex queries. Finally, we summarize the
                 experience gained in Monet by creating a highly
                 efficient implementation of MIL.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database systems; main-memory techniques; query
                 languages; query optimization; vertical fragmentation",
  remark =       "Check month: April or May??",
}

@Article{Aslan:1999:SHR,
  author =       "Goksel Aslan and Dennis McLeod",
  title =        "Semantic Heterogeneity Resolution in Federated
                 Databases by Metadata Implantation and Stepwise
                 Evolution",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "2",
  pages =        "120--132",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:50 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Aslan:Goksel.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/McLeod:Dennis.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008002/90080120.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008002/90080120.pdf",
  abstract =     "A key aspect of interoperation among data-intensive
                 systems involves the mediation of metadata and
                 ontologies across database boundaries. One way to
                 achieve such mediation between a local database and a
                 remote database is to fold remote metadata into the
                 local metadata, thereby creating a common platform
                 through which information sharing and exchange becomes
                 possible. Schema implantation and semantic evolution,
                 our approach to the metadata folding problem, is a
                 partial database integration scheme in which remote and
                 local (meta)data are integrated in a stepwise manner
                 over time. We introduce metadata implantation and
                 stepwise evolution techniques to interrelate database
                 elements in different databases, and to resolve
                 conflicts on the structure and semantics of database
                 elements (classes, attributes, and individual
                 instances). We employ a semantically rich canonical
                 data model, and an incremental integration and semantic
                 heterogeneity resolution scheme. In our approach,
                 relationships between local and remote information
                 units are determined whenever enough knowledge about
                 their semantics is acquired. The metadata folding
                 problem is solved by implanting remote database
                 elements into the local database, a process that
                 imports remote database elements into the local
                 database environment, hypothesizes the relevance of
                 local and remote classes, and customizes the
                 organization of remote metadata. We have implemented a
                 prototype system and demonstrated its use in an
                 experimental neuroscience environment.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database integration; database interoperability;
                 federated databases; schema evolution; semantic
                 heterogeneity resolution",
  remark =       "Check month: April or May??",
}

@Article{Law:1999:ESI,
  author =       "Kelvin K. W. Law and John C. S. Lui and Leana
                 Golubchik",
  title =        "Efficient Support for Interactive Service in
                 Multi-Resolution {VOD} Systems",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "2",
  pages =        "133--153",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:50 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t9008002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Golubchik:Leana.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Law:Kelvin_K=_W=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lui:John_C=_S=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/9008002/90080133.htm;
                 http://link.springer.de/link/service/journals/00778/papers/9008002/90080133.pdf",
  abstract =     "Advances in high-speed networks and multimedia
                 technologies have made it feasible to provide
                 video-on-demand (VOD) services to users. However, it is
                 still a challenging task to design a cost-effective VOD
                 system that can support a large number of clients (who
                 may have different quality of service (QoS)
                 requirements) and, at the same time, provide different
                 types of VCR functionalities. Although it has been
                 recognized that VCR operations are important
                 functionalities in providing VOD service, techniques
                 proposed in the past for providing VCR operations may
                 require additional system resources, such as extra disk
                 I/O, additional buffer space, as well as network
                 bandwidth. In this paper, we consider the design of a
                 VOD storage server that has the following features: (1)
                 provision of different levels of display resolutions to
                 users who have different QoS requirements, (2)
                 provision of different types of VCR functionalities,
                 such as fast forward and rewind, without imposing
                 additional demand on the system buffer space, I/O
                 bandwidth, and network bandwidth, and (3) guarantees of
                 the load-balancing property across all disks during
                 normal and VCR display periods. The above-mentioned
                 features are especially important because they simplify
                 the design of the buffer space, I/O, and network
                 resource allocation policies of the VOD storage system.
                 The load-balancing property also ensures that no single
                 disk will be the bottleneck of the system. In this
                 paper, we propose data block placement, admission
                 control, and I/O-scheduling algorithms, as well as
                 determine the corresponding buffer space requirements
                 of the proposed VOD storage system. We show that the
                 proposed VOD system can provide VCR and
                 multi-resolution services to the viewing clients and at
                 the same time maintain the load-balancing property.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "interactive services; multi-resolution services;
                 multimedia servers; VOD systems",
  remark =       "Check month: April or May??",
}

@Article{Shmueli:2000:FVP,
  author =       "O. Shmueli and J. Widom",
  title =        "Foreword by the {VLDB} `98 {PC Chairmen}",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "155--155",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Widom:2000:BPV,
  author =       "Jennifer Widom and Oded Shmueli",
  title =        "Best Papers of {VLDB `98, New York: Foreword by the
                 VLDB `98 PC Chairmen: Best Papers of VLDB `98}",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "155--155",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 10:11:55 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Shmueli:Oded.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Widom:Jennifer.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080155.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080155.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  xxauthor =     "O. Shmueli and J. Widom",
}

@Article{Braumandl:2000:FJP,
  author =       "Reinhard Braumandl and Jens Clau{\ss}en and Alfons
                 Kemper and Donald Kossmann",
  title =        "Functional-Join Processing",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "156--177",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Braumandl:Reinhard.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Clau=szlig=en:Jens.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kemper:Alfons.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kossmann:Donald.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080156.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080156.pdf",
  abstract =     "Inter-object references are one of the key concepts of
                 object-relational and object-oriented database systems.
                 In this work, we investigate alternative techniques to
                 implement inter-object references and make the best use
                 of them in query processing, i.e., in evaluating
                 functional joins. We will give a comprehensive overview
                 and performance evaluation of all known techniques for
                 simple (single-valued) as well as multi-valued
                 functional joins. Furthermore, we will describe special
                 {\em order-preserving\/\/} functional-join techniques
                 that are particularly attractive for decision support
                 queries that require ordered results. While most of the
                 presentation of this paper is focused on
                 object-relational and object-oriented database systems,
                 some of the results can also be applied to plain
                 relational databases because {\em index nested-loop
                 joins\/\/} along key/foreign-key relationships, as they
                 are frequently found in relational databases, are just
                 one particular way to execute a functional join.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "functional join; logical OID; object identifier;
                 order-preserving join; physical OID; pointer join;
                 query processing",
}

@Article{George:2000:SBF,
  author =       "Binto George and Jayant R. Haritsa",
  title =        "Secure Buffering in Firm Real-Time Database Systems",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "178--198",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/George:Binto.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/h/Haritsa:Jayant_R=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080178.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080178.pdf",
  abstract =     "Many real-time database applications arise in
                 electronic financial services, safety-critical
                 installations and military systems where enforcing is
                 crucial to the success of the enterprise. We
                 investigate here the performance implications, in terms
                 of killed transactions, of guaranteeing {\em
                 multi-level secrecy\/} in a real-time database system
                 supporting applications with {\em firm\/} deadlines. In
                 particular, we focus on the {\em buffer management\/}
                 aspects of this issue. Our main contributions are the
                 following. First, we identify the importance and
                 difficulties of providing secure buffer management in
                 the real-time database environment. Second, we present
                 , a novel buffer management algorithm that provides
                 {\em covert-channel-free\/} security. SABRE employs a
                 fully dynamic one-copy allocation policy for efficient
                 usage of buffer resources. It also incorporates several
                 optimizations for reducing the overall number of killed
                 transactions and for decreasing the unfairness in the
                 distribution of killed transactions across security
                 levels. Third, using a detailed simulation model, the
                 real-time performance of SABRE is evaluated against
                 unsecure conventional and real-time buffer management
                 policies for a variety of security-classified
                 transaction workloads and system configurations. Our
                 experiments show that SABRE provides security with only
                 a modest drop in real-time performance. Finally, we
                 evaluate SABRE's performance when augmented with the
                 GUARD adaptive admission control policy. Our
                 experiments show that this combination provides close
                 to ideal fairness for real-time applications that can
                 tolerate covert-channel bandwidths of up to one bit per
                 second (a limit specified in military standards).",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "buffer management; covert channels; firm deadlines;
                 real-time database",
}

@Article{Muth:2000:LLS,
  author =       "Peter Muth and Patrick E. O'Neil and Achim Pick and
                 Gerhard Weikum",
  title =        "The {LHAM} Log-Structured History Data Access Method",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "199--221",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Muth:Peter.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/o/O=Neil:Patrick_E=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Pick:Achim.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/w/Weikum:Gerhard.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080199.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080199.pdf",
  abstract =     "Numerous applications such as stock market or medical
                 information systems require that both historical and
                 current data be logically integrated into a temporal
                 database. The underlying access method must support
                 different forms of ``time-travel'' queries, the
                 migration of old record versions onto inexpensive
                 archive media, and high insertion and update rates.
                 This paper presents an access method for
                 transaction-time temporal data, called the
                 log-structured history data access method (LHAM) that
                 meets these demands. The basic principle of LHAM is to
                 partition the data into successive components based on
                 the timestamps of the record versions. Components are
                 assigned to different levels of a storage hierarchy,
                 and incoming data is continuously migrated through the
                 hierarchy. The paper discusses the LHAM concepts,
                 including concurrency control and recovery, our
                 full-fledged LHAM implementation, and experimental
                 performance results based on this implementation. A
                 detailed comparison with the TSB-tree, both
                 analytically and based on experiments with real
                 implementations, shows that LHAM is highly superior in
                 terms of insert performance, while query performance is
                 in almost all cases at least as good as for the
                 TSB-tree; in many cases it is much better.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data warehouses; index structures; performance;
                 storage systems; temporal databases",
}

@Article{Gibson:2000:CCD,
  author =       "David Gibson and Jon M. Kleinberg and Prabhakar
                 Raghavan",
  title =        "Clustering Categorical Data: An Approach Based on
                 Dynamical Systems",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "222--236",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Gibson:David.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kleinberg:Jon_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Raghavan:Prabhakar.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080222.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080222.pdf",
  abstract =     "We describe a novel approach for clustering
                 collections of sets, and its application to the
                 analysis and mining of categorical data. By
                 ``categorical data,'' we mean tables with fields that
                 cannot be naturally ordered by a metric --- e.g., the
                 names of producers of automobiles, or the names of
                 products offered by a manufacturer. Our approach is
                 based on an iterative method for assigning and
                 propagating weights on the categorical values in a
                 table; this facilitates a type of similarity measure
                 arising from the co-occurrence of values in the
                 dataset. Our techniques can be studied analytically in
                 terms of certain types of non-linear dynamical
                 systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "categorical data; clustering; data mining; dynamical
                 systems; hypergraphs",
}

@Article{Knorr:2000:DBO,
  author =       "Edwin M. Knorr and Raymond T. Ng and Vladimir
                 Tucakov",
  title =        "Distance-Based Outliers: Algorithms and Applications",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "237--253",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Knorr:Edwin_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/n/Ng:Raymond_T=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tucakov:V=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080237.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080237.pdf",
  abstract =     "This paper deals with finding outliers (exceptions) in
                 large, multidimensional datasets. The identification of
                 outliers can lead to the discovery of truly unexpected
                 knowledge in areas such as electronic commerce, credit
                 card fraud, and even the analysis of performance
                 statistics of professional athletes. Existing methods
                 that we have seen for finding outliers can only deal
                 efficiently with two dimensions/attributes of a
                 dataset. In this paper, we study the notion of {\em
                 DB\/} ({\em distance-based\/}) outliers. Specifically,
                 we show that (i) outlier detection can be done {\em
                 efficiently\/} for {\em large\/} datasets, and for
                 $k$-dimensional datasets with large values of $k$
                 (e.g., $k \ge 5$); and (ii), outlier detection is a
                 {\em meaningful\/} and important knowledge discovery
                 task. First, we present two simple algorithms, both
                 having a complexity of $O(k \: N^2)$, $k$ being the
                 dimensionality and $N$ being the number of objects in
                 the dataset. These algorithms readily support datasets
                 with many more than two attributes. Second, we present
                 an optimized cell-based algorithm that has a complexity
                 that is linear with respect to $N$, but exponential
                 with respect to $k$. We provide experimental results
                 indicating that this algorithm significantly
                 outperforms the two simple algorithms for $k \leq 4$.
                 Third, for datasets that are mainly disk-resident, we
                 present another version of the cell-based algorithm
                 that guarantees at most three passes over a dataset.
                 Again, experimental results show that this algorithm is
                 by far the best for $k \leq 4$. Finally, we discuss our
                 work on three real-life applications, including one on
                 spatio-temporal data (e.g., a video surveillance
                 application), in order to confirm the relevance and
                 broad applicability of {\em DB\/} outliers.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "algorithms; data mining; data mining applications;
                 outliers\slash exceptions",
}

@Article{Korn:2000:QDM,
  author =       "Flip Korn and Alexandros Labrinidis and Yannis Kotidis
                 and Christos Faloutsos",
  title =        "Quantifiable Data Mining Using Ratio Rules",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "254--266",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Faloutsos:Christos.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Korn:Flip.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/k/Kotidis:Yannis.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Labrinidis:Alexandros.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080254.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080254.pdf",
  abstract =     "Association Rule Mining algorithms operate on a data
                 matrix (e.g., customers $\times$ products) to derive
                 association rules [AIS93b, SA96]. We propose a new
                 paradigm, namely, {\em Ratio Rules}, which are
                 quantifiable in that we can measure the ``goodness'' of
                 a set of discovered rules. We also propose the
                 ``guessing error'' as a measure of the ``goodness'',
                 that is, the root-mean-square error of the
                 reconstructed values of the cells of the given matrix,
                 when we pretend that they are unknown. Another
                 contribution is a novel method to guess missing/hidden
                 values from the Ratio Rules that our method derives.
                 For example, if somebody bought $10 of milk and $3 of
                 bread, our rules can ``guess'' the amount spent on
                 butter. Thus, unlike association rules, Ratio Rules can
                 perform a variety of important tasks such as
                 forecasting, answering ``what-if'' scenarios, detecting
                 outliers, and visualizing the data. Moreover, we show
                 that we can compute Ratio Rules in a {\em single\/}
                 pass over the data set with small memory requirements
                 (a few small matrices), in contrast to association rule
                 mining methods which require multiple passes and/or
                 large memory. Experiments on several real data sets
                 (e.g., basketball and baseball statistics, biological
                 data) demonstrate that the proposed method: (a) leads
                 to rules that make sense; (b) can find large itemsets
                 in binary matrices, even in the presence of noise; and
                 (c) consistently achieves a ``guessing error'' of up to
                 5 times less than using straightforward column
                 averages.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data mining; forecasting; guessing error; knowledge
                 discovery",
}

@Article{Torp:2000:ETD,
  author =       "Kristian Torp and Christian S. Jensen and Richard
                 Thomas Snodgrass",
  title =        "Effective Timestamping in Databases",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "267--288",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/j/Jensen:Christian_S=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Snodgrass:Richard_T=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Torp:Kristian.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080267.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080267.pdf",
  abstract =     "Many existing database applications place various
                 timestamps on their data, rendering temporal values
                 such as dates and times prevalent in database tables.
                 During the past two decades, several dozen temporal
                 data models have appeared, all with timestamps being
                 integral components. The models have used timestamps
                 for encoding two specific temporal aspects of database
                 facts, namely transaction time, when the facts are
                 current in the database, and valid time, when the facts
                 are true in the modeled reality. However, with few
                 exceptions, the assignment of timestamp values has been
                 considered only in the context of individual
                 modification statements. This paper takes the next
                 logical step: It considers the use of timestamping for
                 capturing transaction and valid time in the context of
                 transactions. The paper initially identifies and
                 analyzes several problems with straightforward
                 timestamping, then proceeds to propose a variety of
                 techniques aimed at solving these problems.
                 Timestamping the results of a transaction with the
                 commit time of the transaction is a promising approach.
                 The paper studies how this timestamping may be done
                 using a spectrum of techniques. While many database
                 facts are valid until {\em now}, the current time, this
                 value is absent from the existing temporal types.
                 Techniques that address this problem using different
                 substitute values are presented. Using a stratum
                 architecture, the performance of the different proposed
                 techniques are studied. Although querying and modifying
                 time-varying data is accompanied by a number of subtle
                 problems, we present a comprehensive approach that
                 provides application programmers with simple,
                 consistent, and efficient support for modifying
                 bitemporal databases in the context of user
                 transactions.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "timestamping; transactions",
}

@Article{Sheikholeslami:2000:WWB,
  author =       "Gholamhosein Sheikholeslami and Surojit Chatterjee and
                 Aidong Zhang",
  title =        "{WaveCluster}: {A} Wavelet Based Clustering Approach
                 for Spatial Data in Very Large Databases",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "289--304",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chatterjee:Surojit.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sheikholeslami:Gholamhosein.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Zhang:Aidong.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080289.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080289.pdf",
  abstract =     "Many applications require the management of spatial
                 data in a multidimensional feature space. Clustering
                 large spatial databases is an important problem, which
                 tries to find the densely populated regions in the
                 feature space to be used in data mining, knowledge
                 discovery, or efficient information retrieval. A good
                 clustering approach should be efficient and detect
                 clusters of arbitrary shape. It must be insensitive to
                 the noise (outliers) and the order of input data. We
                 propose {\em WaveCluster}, a novel clustering approach
                 based on wavelet transforms, which satisfies all the
                 above requirements. Using the multiresolution property
                 of wavelet transforms, we can effectively identify
                 arbitrarily shaped clusters at different degrees of
                 detail. We also demonstrate that {\em WaveCluster\/} is
                 highly efficient in terms of time complexity.
                 Experimental results on very large datasets are
                 presented, which show the efficiency and effectiveness
                 of the proposed approach compared to the other recent
                 clustering methods.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Pacitti:2000:UPS,
  author =       "Esther Pacitti and Eric Simon",
  title =        "Update Propagation Strategies to Improve Freshness in
                 Lazy Master Replicated Databases",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "305--318",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Pacitti:Esther.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Simon:Eric.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080305.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080305.pdf",
  abstract =     "Many distributed database applications need to
                 replicate data to improve data availability and query
                 response time. The two-phase commit protocol guarantees
                 mutual consistency of replicated data but does not
                 provide good performance. Lazy replication has been
                 used as an alternative solution in several types of
                 applications such as on-line financial transactions and
                 telecommunication systems. In this case, mutual
                 consistency is relaxed and the concept of freshness is
                 used to measure the deviation between replica copies.
                 In this paper, we propose two update propagation
                 strategies that improve freshness. Both of them use
                 immediate propagation: updates to a primary copy are
                 propagated towards a slave node as soon as they are
                 detected at the master node without waiting for the
                 commitment of the update transaction. Our performance
                 study shows that our strategies can improve data
                 freshness by up to five times compared with the
                 deferred approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data replication; distributed databases; performance
                 evaluation",
}

@Article{Liang:2000:OMD,
  author =       "Weifa Liang and Maria E. Orlowska and Jeffrey X. Yu",
  title =        "Optimizing Multiple Dimensional Queries Simultaneously
                 in Multidimensional Databases",
  journal =      j-VLDB-J,
  volume =       "8",
  number =       "3--4",
  pages =        "319--338",
  month =        feb,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:51 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb8.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0008003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Liang:Weifa.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/o/Orlowska:Maria_E=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/y/Yu:Jeffrey_X=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0008003/00080319.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0008003/00080319.pdf",
  abstract =     "Some significant progress related to multidimensional
                 data analysis has been achieved in the past few years,
                 including the design of fast algorithms for computing
                 datacubes, selecting some precomputed group-bys to
                 materialize, and designing efficient storage structures
                 for multidimensional data. However, little work has
                 been carried out on multidimensional query optimization
                 issues. Particularly the response time (or evaluation
                 cost) for answering several related dimensional queries
                 simultaneously is crucial to the OLAP applications.
                 Recently, Zhao et al. first exploited this problem by
                 presenting three heuristic algorithms. In this paper we
                 first consider in detail two cases of the problem in
                 which all the queries are either hash-based star joins
                 or index-based star joins only. In the case of the
                 hash-based star join, we devise a polynomial
                 approximation algorithm which delivers a plan whose
                 evaluation cost is $O(n^\epsilon)$ times the optimal,
                 where $n$ is the number of queries and $\epsilon$ is a
                 fixed constant with $0 < \epsilon \leq 1$. We also
                 present an exponential algorithm which delivers a plan
                 with the optimal evaluation cost. In the case of the
                 index-based star join, we present a heuristic algorithm
                 which delivers a plan whose evaluation cost is $n$
                 times the optimal, and an exponential algorithm which
                 delivers a plan with the optimal evaluation cost. We
                 then consider a general case in which both hash-based
                 star-join and index-based star-join queries are
                 included. For this case, we give a possible improvement
                 on the work of Zhao et al., based on an analysis of
                 their solutions. We also develop another heuristic and
                 an exact algorithm for the problem. We finally conduct
                 a performance study by implementing our algorithms. The
                 experimental results demonstrate that the solutions
                 delivered for the restricted cases are always within
                 two times of the optimal, which confirms our
                 theoretical upper bounds. Actually these experiments
                 produce much better results than our theoretical
                 estimates. To the best of our knowledge, this is the
                 only development of polynomial algorithms for the first
                 two cases which are able to deliver plans with
                 deterministic performance guarantees in terms of the
                 qualities of the plans generated. The previous
                 approaches including that of [ZDNS98] may generate a
                 feasible plan for the problem in these two cases, but
                 they do not provide any performance guarantee, i.e.,
                 the plans generated by their algorithms can be
                 arbitrarily far from the optimal one.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data warehousing; MDDBs; multiple dimensional query
                 optimization; OLAP; query modeling",
}

@Article{Atzeni:2000:DWG,
  author =       "Paolo Atzeni and Alberto O. Mendelzon",
  title =        "Databases and the {Web}: Guest Editorial: Databases
                 and the {Web}",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "1",
  pages =        "1--1",
  month =        mar,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Sep 27 10:11:55 MDT 2000",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009001.htm;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/a/Atzeni:Paolo.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mendelzon:Alberto_O=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009001/00090001.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009001/00090001.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Atzeni:2000:GE,
  author =       "Paolo Atzeni and Alberto O. Mendelzon",
  title =        "Guest editorial",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "1",
  pages =        "1--1",
  month =        mar,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:52 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Chidlovskii:2000:SCW,
  author =       "Boris Chidlovskii and Uwe M. Borghoff",
  title =        "Semantic caching of {Web} queries",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "1",
  pages =        "2--17",
  month =        mar,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:52 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Borghoff:Uwe_M=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chidlovskii:Boris.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009001/00090002.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009001/00090002.pdf",
  abstract =     "In meta-searchers accessing distributed Web-based
                 information repositories, performance is a major issue.
                 Efficient query processing requires an appropriate
                 caching mechanism. Unfortunately, standard page-based
                 as well as tuple-based caching mechanisms designed for
                 conventional databases are not efficient on the Web,
                 where keyword-based querying is often the only way to
                 retrieve data. In this work, we study the problem of
                 semantic caching of Web queries and develop a caching
                 mechanism for conjunctive Web queries based on {\em
                 signature files}. Our algorithms cope with both
                 relations of semantic containment and intersection
                 between a query and the corresponding cache items. We
                 also develop the cache replacement strategy to treat
                 situations when cached items differ in size and
                 contribution when providing partial query answers. We
                 report results of experiments and show how the caching
                 mechanism is realized in the Knowledge Broker system.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "experiments; query algorithms; region containment;
                 semantic caching; signature files",
}

@Article{Gruser:2000:LRT,
  author =       "Jean-Robert Gruser and Louiqa Raschid and Vladimir
                 Zadorozhny and Tao Zhan",
  title =        "Learning response time for {WebSources} using query
                 feedback and application in query optimization",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "1",
  pages =        "18--37",
  month =        mar,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:52 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/g/Gruser:Jean=Robert.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/r/Raschid:Louiqa.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Zadorozhny:Vladimir.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/z/Zhan:Tao.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009001/00090018.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009001/00090018.pdf",
  abstract =     "The rapid growth of the Internet and support for
                 interoperability protocols has increased the number of
                 Web accessible sources, WebSources. Current wrapper
                 mediator architectures need to be extended with a
                 wrapper cost model (WCM) for WebSources that can
                 estimate the response time (delays) to access sources
                 as well as other relevant statistics. In this paper, we
                 present a Web prediction tool (WebPT), a tool that is
                 based on learning using query feedback from WebSources.
                 The WebPT uses dimensions time of day, day, and
                 quantity of data, to learn response times from a
                 particular WebSource, and to predict the expected
                 response time (delay) for some query. Experiment data
                 was collected from several sources, and those
                 dimensions that were significant in estimating the
                 response time were determined. We then trained the
                 WebPT on the collected data, to use the three
                 dimensions mentioned above, and to predict the response
                 time, as well as a confidence in the prediction. We
                 describe the WebPT learning algorithms, and report on
                 the WebPT learning for WebSources. Our research shows
                 that we can improve the quality of learning by tuning
                 the WebPT features, e.g., training the WebPT using a
                 logarithm of the input training data; including
                 significant dimensions in the WebPT; or changing the
                 ordering of dimensions. A comparison of the WebPT with
                 more traditional neural network (NN) learning has been
                 performed, and we briefly report on the comparison. We
                 then demonstrate how the WebPT prediction of delay may
                 be used by a scrambling enabled optimizer. A scrambling
                 algorithm identifies some critical points of delay,
                 where it makes a decision to scramble (modify) a plan,
                 to attempt to hide the expected delay by computing some
                 other part of the plan that is unaffected by the delay.
                 We explore the space of real delay at a WebSource,
                 versus the WebPT prediction of this delay, with respect
                 to critical points of delay in specific plans. We
                 identify those cases where WebPT overestimation or
                 underestimation of the real delay results in a penalty
                 in the scrambling enabled optimizer, and those cases
                 where there is no penalty. Using the experimental data
                 and WebPT learning, we test how good the WebPT is in
                 minimizing these penalties.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data-intensive applications on the Web; query
                 languages and systems for Web data",
}

@Article{Fernandez:2000:DSW,
  author =       "Mary Fern{\'a}ndez and Daniela Florescu and Alon Levy
                 and Dan Suciu",
  title =        "Declarative specification of {Web} sites with {S}",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "1",
  pages =        "38--55",
  month =        mar,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:52 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Fernandez:Mary_F=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Florescu:Daniela.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Levy:Alon_Y=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Suciu:Dan.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009001/00090038.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009001/00090038.pdf",
  abstract =     "S is a system for implementing {\em data-intensive\/}
                 Web sites, which typically integrate information from
                 multiple data sources and have complex structure. S's
                 key idea is separating the management of a Web site's
                 data, the specification of its content and structure,
                 and the visual representation of its pages. S provides
                 a declarative {\em query language\/} for specifying a
                 site's content and structure, and a simple {\em
                 template language\/} for specifying a site's HTML
                 representation. This paper contains a comprehensive
                 description of the S system and details the benefits of
                 declarative site specification. We describe our
                 experiences using S in a production application and
                 describe three different, but complementary, systems
                 that extend and improve upon S's original ideas.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "declarative query languages; web-site management",
  xxauthor =     "Mary F. Fernandez and Daniela Florescu and Alon Y.
                 Levy and Dan Suciu",
  xxtitle =      "Declarative Specification of {Web} Sites with
                 {Strudel}",
}

@Article{Berendt:2000:ANB,
  author =       "Bettina Berendt and Myra Spiliopoulou",
  title =        "Analysis of navigation behaviour in {Web} sites
                 integrating multiple information systems",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "1",
  pages =        "56--75",
  month =        mar,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:52 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Berendt:Bettina.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Spiliopoulou:Myra.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009001/00090056.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009001/00090056.pdf",
  abstract =     "The analysis of web usage has mostly focused on sites
                 composed of conventional static pages. However, huge
                 amounts of information available in the web come from
                 databases or other data collections and are presented
                 to the users in the form of dynamically generated
                 pages. The query interfaces of such sites allow the
                 specification of many search criteria. Their generated
                 results support navigation to pages of results
                 combining cross-linked data from many sources. For the
                 analysis of visitor navigation behaviour in such web
                 sites, we propose the web usage miner (WUM), which
                 discovers navigation patterns subject to advanced
                 statistical and structural constraints. Since our
                 objective is the discovery of interesting navigation
                 patterns, we do not focus on accesses to individual
                 pages. Instead, we construct conceptual hierarchies
                 that reflect the query capabilities used in the
                 production of those pages. Our experiments with a real
                 web site that integrates data from multiple databases,
                 the German SchulWeb, demonstrate the appropriateness of
                 WUM in discovering navigation patterns and show how
                 those discoveries can help in assessing and improving
                 the quality of the site.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "conceptual hierarchies; data mining; query
                 capabilities; Web databases; Web query interfaces; Web
                 usage mining",
}

@Article{Buneman:2000:UQL,
  author =       "Peter Buneman and Mary F. Fernandez and Dan Suciu",
  title =        "{UnQL}: a query language and algebra for
                 semistructured data based on structural recursion",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "1",
  pages =        "76--110",
  month =        mar,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:52 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/b/Buneman:Peter.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Fernandez:Mary_F=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Suciu:Dan.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009001/00090076.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009001/00090076.pdf",
  abstract =     "This paper presents structural recursion as the basis
                 of the syntax and semantics of query languages for
                 semistructured data and XML. We describe a simple and
                 powerful query language based on pattern matching and
                 show that it can be expressed using structural
                 recursion, which is introduced as a top-down, recursive
                 function, similar to the way XSL is defined on XML
                 trees. On cyclic data, structural recursion can be
                 defined in two equivalent ways: as a recursive function
                 which evaluates the data top-down and remembers all its
                 calls to avoid infinite loops, or as a bulk evaluation
                 which processes the entire data in parallel using only
                 traditional relational algebra operators. The latter
                 makes it possible for optimization techniques in
                 relational queries to be applied to structural
                 recursion. We show that the composition of two
                 structural recursion queries can be expressed as a
                 single such query, and this is used as the basis of an
                 optimization method for mediator systems. Several other
                 formal properties are established: structural recursion
                 can be expressed in first-order logic extended with
                 transitive closure; its data complexity is PTIME; and
                 over relational data it is a conservative extension of
                 the relational calculus. The underlying data model is
                 based on value equality, formally defined with
                 bisimulation. Structural recursion is shown to be
                 invariant with respect to value equality.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "optimization; query language; semistructured data;
                 structural recursion; XML; XSL",
}

@Article{Mirbel:2000:CTI,
  author =       "Isabelle Mirbel and Barbara Pernici and Timos K.
                 Sellis and S. Tserkezoglou and Michalis Vazirgiannis",
  title =        "Checking the Temporal Integrity of Interactive
                 Multimedia Documents",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "2",
  pages =        "111--130",
  month =        jul,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:53 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Mirbel:Isabelle.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/p/Pernici:Barbara.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Sellis:Timos_K=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/t/Tserkezoglou:S=.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/v/Vazirgiannis:Michalis.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009002/00090111.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009002/00090111.pdf",
  abstract =     "When authoring multimedia scenarios, and in particular
                 scenarios with user interaction, where the sequence and
                 time of occurrence of interactions is not predefined,
                 it is difficult to guarantee the consistency of the
                 resulting scenarios. As a consequence, the {\em
                 execution\/} of the scenario may result in unexpected
                 behavior or inconsistent use of media. The present
                 paper proposes a methodology for checking the temporal
                 integrity of interactive multimedia document (IMD)
                 scenarios at authoring time at various levels. The IMD
                 flow is mainly defined by the events occurring during
                 the IMD session. Integrity checking consists of a set
                 of discrete steps, during which we transform the
                 scenario into temporal constraint networks representing
                 the constraints linking the different possible events
                 in the scenario. Temporal constraint verification
                 techniques are applied to verify the integrity of the
                 scenario, deriving a minimal network, showing possible
                 temporal relationships between events given a set of
                 constraints.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "constraint networks; multimedia presentation; temporal
                 integrity",
}

@Article{Candan:2000:VMM,
  author =       "K. Sel{\c{c}}uk Candan and Eric Lemar and V. S.
                 Subrahmanian",
  title =        "View management in multimedia databases",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "2",
  pages =        "131--153",
  month =        jul,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:53 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Candan:K=_Sel=ccedil=uk.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/l/Lemar:Eric.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/s/Subrahmanian:V=_S=.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009002/00090131.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009002/00090131.pdf",
  abstract =     "Though there has been extensive work on multimedia
                 databases in the last few years, there is no prevailing
                 notion of a multimedia view, nor there are techniques
                 to create, manage, and maintain such views. Visualizing
                 the results of a dynamic multimedia query or
                 materializing a dynamic multimedia view corresponds to
                 assembling and delivering an interactive multimedia
                 presentation in accordance with the visualization
                 specifications. In this paper, we suggest that a
                 non-interactive multimedia presentation is a set of
                 {\em virtual objects\/} with associated spatial and
                 temporal presentation constraints. A virtual object is
                 either an object, or the result of a query. As queries
                 may have different answers at different points in time,
                 scheduling the presentation of such objects is
                 nontrivial. We then develop a probabilistic model of
                 interactive multimedia presentations, extending the
                 non-interactive model described earlier. We also
                 develop a probabilistic model of interactive
                 visualization where the probabilities reflect the user
                 profiles, or the likelihood of certain user
                 interactions. Based on this probabilistic model, we
                 develop three utility-theoretic based types of
                 prefetching algorithms that anticipate how users will
                 interact with the presentation. These prefetching
                 algorithms allow efficient visualization of the query
                 results in accordance with the underlying
                 specification. We have built a prototype system that
                 incorporates these algorithms. We report on the results
                 of experiments conducted on top of this
                 implementation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "interactivity; multimedia databases; prefetching;
                 result visualization\slash presentation; view
                 management",
}

@Article{Fu:2000:DVT,
  author =       "Ada Wai-chee Fu and Polly Mei-shuen Chan and Yin-Ling
                 Cheung and Yiu Sang Moon",
  title =        "Dynamic vp-Tree Indexing for $n$-Nearest Neighbor
                 Search Given Pair-Wise Distances",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "2",
  pages =        "154--173",
  month =        jul,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:53 MDT 2008",
  bibsource =    "http://ftp.informatik.rwth-aachen.de/dblp/db/journals/vldb/vldb9.html;
                 http://link.springer.de/link/service/journals/00778/tocs/t0009002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Electronic edition.",
  URL =          "http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Chan:Polly_Mei=shuen.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/c/Cheung:Yin=Ling.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/f/Fu:Ada_Wai=Chee.html;
                 http://ftp.informatik.rwth-aachen.de/dblp/db/indices/a-tree/m/Moon:Yiu_Sang.html;
                 http://link.springer.de/link/service/journals/00778/bibs/0009002/00090154.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009002/00090154.pdf",
  abstract =     "For some multimedia applications, it has been found
                 that domain objects cannot be represented as feature
                 vectors in a multidimensional space. Instead, pair-wise
                 distances between data objects are the only input. To
                 support content-based retrieval, one approach maps each
                 object to a $k$dimensional ($k$d) point and tries to
                 preserve the distances among the points. Then, existing
                 spatial access index methods such as the R-trees and
                 KD-trees can support fast searching on the resulting
                 $k$d points. However, information loss is inevitable
                 with such an approach since the distances between data
                 objects can only be preserved to a certain extent. Here
                 we investigate the use of a distance-based indexing
                 method. In particular, we apply the vantage point tree
                 (vp-tree) method. There are two important problems for
                 the vp-tree method that warrant further investigation,
                 the $n$nearest neighbors search and the updating
                 mechanisms. We study an $n$nearest neighbors search
                 algorithm for the vp-tree, which is shown by
                 experiments to scale up well with the size of the
                 dataset and the desired number of nearest neighbors,
                 $n$. Experiments also show that the searching in the
                 vp-tree is more efficient than that for the $R^*$-tree
                 and the $M$-tree. Next, we propose solutions for the
                 update problem for the vp-tree, and show by experiments
                 that the algorithms are efficient and effective.
                 Finally, we investigate the problem of selecting
                 vantage-point, propose a few alternative methods, and
                 study their impact on the number of distance
                 computation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "content-based retrieval; indexing; nearest neighbor
                 search; pair-wise distances; updating",
}

@Article{Atkinson:2000:GE,
  author =       "Malcolm P. Atkinson",
  title =        "Guest editorial",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "3",
  pages =        "175--176",
  month =        dec,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:54 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t0009003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/0009003/00090175.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009003/00090175.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Bernstein:2000:CBP,
  author =       "Philip A. Bernstein and Shankar Pal and David Shutt",
  title =        "Context-based prefetch --- an optimization for
                 implementing objects on relations",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "3",
  pages =        "177--189",
  month =        dec,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:54 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t0009003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/0009003/00090177.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009003/00090177.pdf",
  abstract =     "When implementing persistent objects on a relational
                 database, a major performance issue is prefetching data
                 to minimize the number of round-trips to the database.
                 This is especially hard with navigational applications,
                 since future accesses are unpredictable. We propose the
                 use of the context in which an object is loaded as a
                 predictor of future accesses, where a context can be a
                 stored collection of relationships, a query result, or
                 a complex object. When an object O's state is loaded,
                 similar state for other objects in O's context is
                 prefetched. We present a design for maintaining context
                 and for using it to guide prefetch. We give performance
                 measurements of its implementation in Microsoft
                 Repository, showing up to a 70\% reduction in running
                 time. We describe several variations of the
                 optimization: selectively applying the technique based
                 on application and database characteristics, using
                 application-supplied performance hints, using
                 concurrent database queries to support asynchronous
                 prefetch, prefetching across relationship paths, and
                 delayed prefetch to save database round-trips.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "caching; object-oriented database; object-relational
                 mapping; prefetch",
}

@Article{Claussen:2000:EES,
  author =       "J. Claussen and A. Kemper and D. Kossmann and C.
                 Wiesner",
  title =        "Exploiting early sorting and early partitioning for
                 decision support query processing",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "3",
  pages =        "190--213",
  month =        dec,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:54 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t0009003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/0009003/00090190.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009003/00090190.pdf",
  abstract =     "Decision support queries typically involve several
                 joins, a grouping with aggregation, and/or sorting of
                 the result tuples. We propose two new classes of query
                 evaluation algorithms that can be used to speed up the
                 execution of such queries. The algorithms are based on
                 (1) {\em early sorting\/} and (2) {\em early
                 partitioning\/} --- or a combination of both. The idea
                 is to push the sorting and/or the partitioning to the
                 leaves, i.e., the base relations, of the query
                 evaluation plans (QEPs) and thereby avoid sorting or
                 partitioning large intermediate results generated by
                 the joins. Both early sorting and early partitioning
                 are used in combination with hash-based algorithms for
                 evaluating the join(s) and the grouping. To enable
                 early sorting, the sort order generated at an early
                 stage of the QEP is retained through an arbitrary
                 number of so-called {\em order-preserving hash joins}.
                 To make early partitioning applicable to a large class
                 of decision support queries, we generalize the
                 so-called hash teams proposed by Graefe et al. [GBC98].
                 Hash teams allow to perform several hash-based
                 operations (join and grouping) on the same attribute in
                 one pass without repartitioning intermediate results.
                 Our generalization consists of indirectly partitioning
                 the input data. Indirect partitioning means
                 partitioning the input data on an attribute that is not
                 directly needed for the next hash-based operation, and
                 it involves the construction of bitmaps to approximate
                 the partitioning for the attribute that is needed in
                 the next hash-based operation. Our performance
                 experiments show that such QEPs based on {\em early
                 sorting, early partitioning}, or both in combination
                 perform significantly better than conventional
                 strategies for many common classes of decision support
                 queries.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "decision support systems; early sorting and
                 partitioning; hash joins and hash teams; performance
                 evaluation; query processing and optimization",
}

@Article{Jagadish:2000:ODM,
  author =       "H. V. Jagadish and Olga Kapitskaia and Raymond T. Ng
                 and Divesh Srivastava",
  title =        "One-dimensional and multi-dimensional substring
                 selectivity estimation",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "3",
  pages =        "214--230",
  month =        dec,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:54 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t0009003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/0009003/00090214.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009003/00090214.pdf",
  abstract =     "With the increasing importance of XML, LDAP
                 directories, and text-based information sources on the
                 Internet, there is an ever-greater need to evaluate
                 queries involving (sub)string matching. In many cases,
                 matches need to be on multiple attributes/dimensions,
                 with correlations between the multiple dimensions.
                 Effective query optimization in this context requires
                 good selectivity estimates. In this paper, we use
                 pruned count-suffix trees (PSTs) as the basic data
                 structure for substring selectivity estimation. For the
                 1-D problem, we present a novel technique called MO
                 (Maximal Overlap). We then develop and analyze two 1-D
                 estimation algorithms, MOC and MOLC, based on MO and a
                 constraint-based characterization of all possible
                 completions of a given PST. For the $k$-D problem, we
                 first generalize PSTs to multiple dimensions and
                 develop a space- and time-efficient probabilistic
                 algorithm to construct $k$-D PSTs directly. We then
                 show how to extend MO to multiple dimensions. Finally,
                 we demonstrate, both analytically and experimentally,
                 that MO is both practical and substantially superior to
                 competing algorithms.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "maximal overlap; pruned count-suffix tree; short
                 memory property; string selectivity",
}

@Article{Manegold:2000:ODA,
  author =       "Stefan Manegold and Peter A. Boncz and Martin L.
                 Kersten",
  title =        "Optimizing database architecture for the new
                 bottleneck: memory access",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "3",
  pages =        "231--246",
  month =        dec,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:54 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t0009003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/0009003/00090231.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009003/00090231.pdf",
  abstract =     "In the past decade, advances in the speed of commodity
                 CPUs have far out-paced advances in memory latency.
                 Main-memory access is therefore increasingly a
                 performance bottleneck for many computer applications,
                 including database systems. In this article, we use a
                 simple scan test to show the severe impact of this
                 bottleneck. The insights gained are translated into
                 guidelines for database architecture, in terms of both
                 data structures and algorithms. We discuss how
                 vertically fragmented data structures optimize cache
                 performance on sequential data access. We then focus on
                 equi-join, typically a random-access operation, and
                 introduce radix algorithms for partitioned hash-join.
                 The performance of these algorithms is quantified using
                 a detailed analytical model that incorporates memory
                 access cost. Experiments that validate this model were
                 performed on the Monet database system. We obtained
                 exact statistics on events such as TLB misses and L1
                 and L2 cache misses by using hardware performance
                 counters found in modern CPUs. Using our cost model, we
                 show how the carefully tuned memory access pattern of
                 our radix algorithms makes them perform well, which is
                 confirmed by experimental results.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "decomposed storage model; implementation techniques;
                 join algorithms; main-memory databases; memory access
                 optimization; query processing",
}

@Article{Raman:2000:ODR,
  author =       "Vijayshankar Raman and Bhaskaran Raman and Joseph M.
                 Hellerstein",
  title =        "Online dynamic reordering",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "3",
  pages =        "247--260",
  month =        dec,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:54 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t0009003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/0009003/00090247.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009003/00090247.pdf",
  abstract =     "We present a pipelining, dynamically tunable {\em
                 reorder\/} operator for providing user control during
                 long running, data-intensive operations. Users can see
                 partial results and accordingly direct the processing
                 by specifying preferences for various data items; data
                 of interest is prioritized for early processing. The
                 reordering mechanism is efficient and non-blocking and
                 can be used over arbitrary data streams from files and
                 indexes, as well as continuous data feeds. We also
                 investigate several policies for the reordering based
                 on the performance goals of various typical
                 applications. We present performance results for
                 reordering in the context of an online aggregation
                 implementation in Informix and in the context of
                 sorting and scrolling in a large-scale spreadsheet. Our
                 experiments demonstrate that for a variety of data
                 distributions and applications, reordering is
                 responsive to dynamic preference changes, imposes
                 minimal overheads in overall completion time, and
                 provides dramatic improvements in the quality of the
                 feedback over time. Surprisingly, preliminary
                 experiments indicate that online reordering can also be
                 useful in traditional batch query processing, because
                 it can serve as a form of pipelined, approximate
                 sorting.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "Informix; interactive data processing; online
                 reordering; user control",
}

@Article{Tan:2000:PEN,
  author =       "Kian-Lee Tan and Cheng Hian Goh and Beng Chin Ooi",
  title =        "Progressive evaluation of nested aggregate queries",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "3",
  pages =        "261--278",
  month =        dec,
  year =         "2000",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:54 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t0009003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/0009003/00090261.htm;
                 http://link.springer.de/link/service/journals/00778/papers/0009003/00090261.pdf",
  abstract =     "In many decision-making scenarios, decision makers
                 require rapid feedback to their queries, which
                 typically involve aggregates. The traditional {\em
                 blocking execution model\/} can no longer meet the
                 demands of these users. One promising approach in the
                 literature, called {\em online aggregation}, evaluates
                 an aggregation query progressively as follows: as soon
                 as certain data have been evaluated, approximate
                 answers are produced with their respective running
                 confidence intervals; as more data are examined, the
                 answers and their corresponding running confidence
                 intervals are refined. In this paper, we extend this
                 approach to handle nested queries with aggregates
                 (i.e., at least one inner query block is an aggregate
                 query) by providing users with (approximate) answers
                 progressively as the inner aggregation query blocks are
                 evaluated. We address the new issues pose by nested
                 queries. In particular, the answer space begins with a
                 superset of the final answers and is refined as the
                 aggregates from the inner query blocks are refined. For
                 the intermediary answers to be meaningful, they have to
                 be interpreted with the aggregates from the inner
                 queries. We also propose a {\em multi-threaded model\/}
                 in evaluating such queries: each query block is
                 assigned to a thread, and the threads can be evaluated
                 concurrently and independently. The time slice across
                 the threads is {\em nondeterministic\/} in the sense
                 that the user controls the relative rate at which these
                 subqueries are being evaluated. For {\em enumerative\/}
                 nested queries, we propose a priority-based evaluation
                 strategy to present answers that are certainly in the
                 final answer space first, before presenting those whose
                 validity may be affected as the inner query aggregates
                 are refined. We implemented a prototype system using
                 Java and evaluated our system. Results for nested
                 queries with a level and multiple levels of nesting are
                 reported. Our results show the effectiveness of the
                 proposed mechanisms in providing progressive feedback
                 that reduces the initial waiting time of users
                 significantly without sacrificing the quality of the
                 answers.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "approximate answers; multi-threading; nested aggregate
                 queries; online aggregation; progressive query
                 processing",
}

@Article{Ngu:2001:CMV,
  author =       "Anne H. H. Ngu and Quan Z. Sheng and Du Q. Huynh and
                 Ron Lei",
  title =        "Combining multi-visual features for efficient indexing
                 in a large image database",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "4",
  pages =        "279--293",
  month =        apr,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100028",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:55 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1009004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1009004/10090279.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1009004/10090279.pdf",
  abstract =     "The optimized distance-based access methods currently
                 available for multidimensional indexing in multimedia
                 databases have been developed based on two major
                 assumptions: a suitable distance function is known a
                 priori and the dimensionality of the image features is
                 low. It is not trivial to define a distance function
                 that best mimics human visual perception regarding
                 image similarity measurements. Reducing
                 high-dimensional features in images using the popular
                 principle component analysis (PCA) might not always be
                 possible due to the non-linear correlations that may be
                 present in the feature vectors. We propose in this
                 paper a fast and robust hybrid method for non-linear
                 dimensions reduction of composite image features for
                 indexing in large image database. This method
                 incorporates both the PCA and non-linear neural network
                 techniques to reduce the dimensions of feature vectors
                 so that an optimized access method can be applied. To
                 incorporate human visual perception into our system, we
                 also conducted experiments that involved a number of
                 subjects classifying images into different classes for
                 neural network training. We demonstrate that not only
                 can our neural network system reduce the dimensions of
                 the feature vectors, but that the reduced dimensional
                 feature vectors can also be mapped to an optimized
                 access method for fast and accurate indexing.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "high-dimensional indexing; image retrieval; neural
                 network",
}

@Article{Combi:2001:HTD,
  author =       "Carlo Combi and Giuseppe Pozzi",
  title =        "{{\em HMAP\/}} --- {A} temporal data model managing
                 intervals with different granularities and
                 indeterminacy from natural language sentences",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "4",
  pages =        "294--311",
  month =        apr,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100033",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:55 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1009004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1009004/10090294.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1009004/10090294.pdf",
  abstract =     "The {\em granularity\/} of given temporal information
                 is the level of abstraction at which information is
                 expressed. Different units of measure allow one to
                 represent different granularities. Indeterminacy is
                 often present in temporal information given at
                 different granularities: temporal {\em indeterminacy\/}
                 is related to incomplete knowledge of when the
                 considered fact happened. Focusing on temporal
                 databases, different granularities and indeterminacy
                 have to be considered in expressing valid time, i.e.,
                 the time at which the information is true in the
                 modeled reality. In this paper, we propose {\em HMAP\/}
                 (The term is the transliteration of an ancient Greek
                 poetical word meaning ``day''.), a temporal data model
                 extending the capability of defining valid times with
                 different granularity and/or with indeterminacy. In
                 {\em HMAP}, absolute intervals are explicitly
                 represented by their {\em start}, {\em end}, and {\em
                 duration\/}: in this way, we can represent valid times
                 as ``in December 1998 for five hours'', ``from July
                 1995, for 15 days'', ``from March 1997 to October 15,
                 1997, between 6 and 6:30 p.m.''. {\em HMAP\/} is based
                 on a three-valued logic, for managing uncertainty in
                 temporal relationships. Formulas involving different
                 temporal relationships between intervals, instants, and
                 durations can be defined, allowing one to query the
                 database with different granularities, not necessarily
                 related to that of data. In this paper, we also discuss
                 the complexity of algorithms, allowing us to evaluate
                 {\em HMAP\/} formulas, and show that the formulas can
                 be expressed as constraint networks falling into the
                 class of simple temporal problems, which can be solved
                 in polynomial time.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "temporal databases; three-valued logic; time
                 granularity; time indeterminacy",
}

@Article{Li:2001:SEM,
  author =       "Wen-Syan Li and K. Sel{\c{c}}uk Candan and Kyoji
                 Hirata and Yoshinori Hara",
  title =        "Supporting efficient multimedia database exploration",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "4",
  pages =        "312--326",
  month =        apr,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100040",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:55 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1009004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1009004/10090312.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1009004/10090312.pdf",
  abstract =     "Due to the fuzziness of query specification and media
                 matching, multimedia retrieval is conducted by way of
                 exploration. It is essential to provide feedback so
                 that users can visualize query reformulation
                 alternatives and database content distribution. Since
                 media matching is an expensive task, another issue is
                 how to efficiently support exploration so that the
                 system is not overloaded by perpetual query
                 reformulation. In this paper, we present a uniform
                 framework to represent statistical information of both
                 semantics and visual metadata for images in the
                 databases. We propose the concept of {\em query
                 verification}, which evaluates queries using
                 statistics, and provides users with feedback, including
                 the strictness and reformulation alternatives of each
                 query condition as well as estimated numbers of
                 matches. With query verification, the system increases
                 the efficiency of the multimedia database exploration
                 for both users and the system. Such statistical
                 information is also utilized to support progressive
                 query processing and query relaxation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "exploration; human computer interaction; multimedia
                 database; progressive processing; query relaxation;
                 selectivity statistics",
}

@Article{Lee:2001:GTM,
  author =       "Chiang Lee and Chi-Sheng Shih and Yaw-Huei Chen",
  title =        "A graph-theoretic model for optimizing queries
                 involving methods",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "4",
  pages =        "327--343",
  month =        apr,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100035",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:55 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1009004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1009004/10090327.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1009004/10090327.pdf",
  abstract =     "Traditional algorithms for optimizing the execution
                 order of joins are no more valid when selections and
                 projections involve methods and become very expensive
                 operations. Selections and projections could be even
                 more costly than joins such that they are pulled above
                 joins, rather than pushed down in a query tree. In this
                 paper, we take a fundamental look at how to approach
                 query optimization from a top-down design perspective,
                 rather than trying to force one model to fit into
                 another. We present a graph model which is designed to
                 characterize execution plans. Each edge and each vertex
                 of the graph is assigned a weight to model execution
                 plans. We also design algorithms that use these weights
                 to optimize the execution order of operations. A cost
                 model of these algorithms is developed. Experiments are
                 conducted on the basis of this cost model. The results
                 show that our algorithms are superior to similar work
                 proposed in the literature.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "graph model; method query; object-oriented databases;
                 query optimization; spanning tree",
}

@Article{Wang:2001:IVH,
  author =       "Changzhou Wang and X. Sean Wang",
  title =        "Indexing very high-dimensional sparse and quasi-sparse
                 vectors for similarity searches",
  journal =      j-VLDB-J,
  volume =       "9",
  number =       "4",
  pages =        "344--361",
  month =        apr,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100036",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:55 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1009004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1009004/10090344.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1009004/10090344.pdf",
  abstract =     "Similarity queries on complex objects are usually
                 translated into searches among their feature vectors.
                 This paper studies indexing techniques for very
                 high-dimensional (e.g., in hundreds) vectors that are
                 sparse or quasi-sparse, i.e., vectors {\em each\/}
                 having only a small number (e.g., ten) of non-zero or
                 significant values. Based on the R-tree, the paper
                 introduces the xS-tree that uses lossy compression of
                 bounding regions to guarantee a reasonable minimum
                 fan-out within the allocated storage space for each
                 node. In addition, the paper studies the performance
                 and scalability of the xS-tree via experiments.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "high-dimensional indexing structure; lossy
                 compression; quasi-sparse vector; similarity search;
                 sparse vector",
}

@Article{Casati:2001:GE,
  author =       "Fabio Casati and Ming-Chien Shan and Dimitrios
                 Georgakopoulos",
  title =        "Guest editorial",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "1--1",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100041",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100001.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100001.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Mecella:2001:DWC,
  author =       "Massimo Mecella and Barbara Pernici",
  title =        "Designing wrapper components for e-services in
                 integrating heterogeneous systems",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "2--15",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100044",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100002.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100002.pdf",
  abstract =     "Component-based approaches are becoming more and more
                 popular to support Internet-based application
                 development. Different component modeling approaches,
                 however, can be adopted, obtaining different
                 abstraction levels (either conceptual or operational).
                 In this paper we present a component-based architecture
                 for the design of e-applications, and discuss the
                 concept of wrapper components as building blocks for
                 the development of e-services, where these services are
                 based on legacy systems. We discuss their
                 characteristics and their applicability in
                 Internet-based application development.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "component; cooperation; e-application; e-service;
                 integration; legacy system; wrapper",
}

@Article{Eyal:2001:ICH,
  author =       "Anat Eyal and Tova Milo",
  title =        "Integrating and customizing heterogeneous e-commerce
                 applications",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "16--38",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100045",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100016.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100016.pdf",
  abstract =     "A broad spectrum of electronic commerce applications
                 is currently available on the Web, providing services
                 in almost any area one can think of. As the number and
                 variety of such applications grow, more business
                 opportunities emerge for providing new services based
                 on the integration and customization of existing
                 applications. (Web shopping malls and support for
                 comparative shopping are just a couple of examples.)
                 Unfortunately, the diversity of applications in each
                 specific domain and the disparity of interfaces,
                 application flows, actor roles in the business
                 transaction, and data formats, renders the integration
                 and manipulation of applications a rather difficult
                 task. In this paper we present the {\em Application
                 Manifold\/} system, aimed at simplifying the intricate
                 task of integration and customization of e-commerce
                 applications. The scope of the work in this paper is
                 limited to web-enabled e-commerce applications. We do
                 not support the integration/customization of
                 proprietary/legacy applications. The wrapping of such
                 applications as web services is complementary to our
                 work. Based on the emerging Web data standard, XML, and
                 application modeling standard, UML, the system offers a
                 novel declarative specification language for describing
                 the integration/customization task, supporting a
                 modular approach where new applications can be added
                 and integrated at will with minimal effort. Then,
                 acting as an application generator, the system
                 generates a full integrated/customized e-commerce
                 application, with the declarativity of the
                 specification allowing for the optimization and
                 verification of the generated application. The
                 integration here deals with the full profile of the
                 given e-commerce applications: the various services
                 offered by the applications, the activities and roles
                 of the different actors participating in the
                 application (e.g., customers, vendors), the application
                 flow, as well as with the data involved in the process.
                 This is in contrast to previous works on Web data
                 integration that focused primarily on querying the data
                 available in the applications, mostly ignoring the
                 additional aspects mentioned above.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "application integration; data integration; electronic
                 commerce",
}

@Article{Bonifati:2001:ARX,
  author =       "Angela Bonifati and Stefano Ceri and Stefano
                 Paraboschi",
  title =        "Active rules for {XML}: {A} new paradigm for
                 {E}-services",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "39--47",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100039",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100039.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100039.pdf",
  abstract =     "XML is rapidly becoming one of the most widely adopted
                 technologies for information exchange and
                 representation. As the use of XML becomes more
                 widespread, we foresee the development of active XML
                 rules, i.e., rules explicitly designed for the
                 management of XML information. In particular, we argue
                 that active rules for XML offer a natural paradigm for
                 the rapid development of innovative e-services. In the
                 paper, we show how active rules can be specified in the
                 context of XSLT, a pattern-based language for
                 publishing XML documents (promoted by the W3C) which is
                 receiving strong commercial support, and Lorel, a query
                 language for XML documents that is quite popular in the
                 research world. We demonstrate, through simple examples
                 of active rules for XSLT and Lorel, that active rules
                 can be effective for the implementation of e-commerce
                 services. We also discuss the various issues that need
                 to be considered in adapting the notion of relational
                 triggers to the XML context.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "active databases; document management; query languages
                 for XML; XML; XSLT",
}

@Article{Braumandl:2001:OUQ,
  author =       "R. Braumandl and M. Keidl and A. Kemper and D.
                 Kossmann and A. Kreutz and S. Seltzsam and K. Stocker",
  title =        "{ObjectGlobe}: {Ubiquitous} query processing on the
                 {Internet}",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "48--71",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100043",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100048.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100048.pdf",
  abstract =     "We present the design of ObjectGlobe, a distributed
                 and open query processor for Internet data sources.
                 Today, data is published on the Internet via Web
                 servers which have, if at all, very localized query
                 processing capabilities. The goal of the ObjectGlobe
                 project is to establish an open marketplace in which
                 {\em data\/} and {\em query processing capabilities\/}
                 can be distributed and used by any kind of Internet
                 application. Furthermore, ObjectGlobe integrates {\em
                 cycle providers\/} (i.e., machines) which carry out
                 query processing operators. The overall picture is to
                 make it possible to execute a query with --- in
                 principle --- unrelated query operators, cycle
                 providers, and data sources. Such an infrastructure can
                 serve as enabling technology for scalable e-commerce
                 applications, e.g., B2B and B2C market places, to be
                 able to integrate data and data processing operations
                 of a large number of participants. One of the main
                 challenges in the design of such an open system is to
                 ensure privacy and security. We discuss the ObjectGlobe
                 security requirements, show how basic components such
                 as the optimizer and runtime system need to be
                 extended, and present the results of performance
                 experiments that assess the additional cost for secure
                 distributed query processing. Another challenge is
                 quality of service management so that users can
                 constrain the costs and running times of their
                 queries.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "cycle-; distributed query processing; function- and
                 data provider; open systems; privacy; quality of
                 service; query optimization; security",
}

@Article{Su:2001:IBN,
  author =       "Stanley Y. W. Su and Chunbo Huang and Joachim Hammer
                 and Yihua Huang and Haifei Li and Liu Wang and Youzhong
                 Liu and Charnyote Pluempitiwiriyawej and Minsoo Lee and
                 Herman Lam",
  title =        "An {Internet-based} negotiation server for
                 e-commerce",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "72--90",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100051",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100072.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100072.pdf",
  abstract =     "This paper describes the design and implementation of
                 a replicable, Internet-based negotiation server for
                 conducting bargaining-type negotiations between
                 enterprises involved in e-commerce and e-business.
                 Enterprises can be buyers and sellers of
                 products/services or participants of a complex supply
                 chain engaged in purchasing, planning, and scheduling.
                 Multiple copies of our server can be installed to
                 complement the services of Web servers. Each enterprise
                 can install or select a trusted negotiation server to
                 represent his/her interests. Web-based GUI tools are
                 used during the build-time registration process to
                 specify the requirements, constraints, and rules that
                 represent negotiation policies and strategies,
                 preference scoring of different data conditions, and
                 aggregation methods for deriving a global cost-benefit
                 score for the item(s) under negotiation. The
                 registration information is used by the negotiation
                 servers to automatically conduct bargaining type
                 negotiations on behalf of their clients. In this paper,
                 we present the architecture of our implementation as
                 well as a framework for automated negotiations, and
                 describe a number of communication primitives which are
                 used in the underlying negotiation protocol. A
                 constraint satisfaction processor (CSP) is used to
                 evaluate a negotiation proposal or counterproposal
                 against the registered requirements and constraints of
                 a client company. In case of a constraint violation, an
                 event is posted to trigger the execution of negotiation
                 strategic rules, which either automatically relax the
                 violated constraint, ask for human intervention, invoke
                 an application, or perform other remedial operations.
                 An Event-Trigger-Rule (ETR) server is used to manage
                 events, triggers, and rules. Negotiation strategic
                 rules can be added or modified at run-time. A
                 cost-benefit analysis component is used to perform
                 quantitative analysis of alternatives. The use of
                 negotiation servers to conduct automated negotiation
                 has been demonstrated in the context of an integrated
                 supply chain scenario.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "constraint evaluation; cost-benefit analysis;
                 database; e-commerce; negotiation policy and strategy;
                 negotiation protocol",
}

@Article{Shegalov:2001:XEW,
  author =       "German Shegalov and Michael Gillmann and Gerhard
                 Weikum",
  title =        "{XML}-enabled workflow management for e-services
                 across heterogeneous platforms",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "91--103",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100038",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100091.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100091.pdf",
  abstract =     "Advanced e-services require efficient, flexible, and
                 easy-to-use workflow technology that integrates well
                 with mainstream Internet technologies such as XML and
                 Web servers. This paper discusses an XML-enabled
                 architecture for distributed workflow management that
                 is implemented in the latest version of our Mentor-lite
                 prototype system. The key asset of this architecture is
                 an XML mediator that handles the exchange of business
                 and flow control data between workflow and
                 business-object servers on the one hand and client
                 activities on the other via XML messages over http. Our
                 implementation of the mediator has made use of Oracle's
                 XSQL servlet. The major benefit of the advocated
                 architecture is that it provides seamless integration
                 of client applications into e-service workflows with
                 scalable efficiency and very little explicit coding, in
                 contrast to an earlier, Java-based, version of our
                 Mentor-lite prototype that required much more code and
                 exhibited potential performance problems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "business processes; information system
                 interoperability; Internet e-services; workflow
                 management; XML/XSL",
}

@Article{Datta:2001:ASS,
  author =       "Anindya Datta and Kaushik Dutta and Debra VanderMeer
                 and Krithi Ramamritham and Shamkant B. Navathe",
  title =        "An architecture to support scalable online
                 personalization on the {Web}",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "1",
  pages =        "104--117",
  month =        aug,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100037",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:56 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010001/10100104.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010001/10100104.pdf",
  abstract =     "Online personalization is of great interest to
                 e-companies. Virtually all personalization technologies
                 are based on the idea of storing as much historical
                 customer session data as possible, and then querying
                 the data store as customers navigate through a web
                 site. The holy grail of online personalization is an
                 environment where fine-grained, detailed historical
                 session data can be queried based on current online
                 navigation patterns for use in formulating real-time
                 responses. Unfortunately, as more consumers become
                 e-shoppers, the user load and the amount of historical
                 data continue to increase, causing scalability-related
                 problems for almost all current personalization
                 technologies. This paper chronicles the development of
                 a real-time interaction management system through the
                 integration of historical data and online visitation
                 patterns of e-commerce site visitors. It describes the
                 scientific underpinnings of the system as well as its
                 architecture. Experimental evaluation of the system
                 shows that the caching and storage techniques built
                 into the system deliver performance that is orders of
                 magnitude better than those derived from off-the-shelf
                 database components.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "behavior-based personalization; dynamic lookahead
                 profile; profile caching; scalable online
                 personalization; Web site and interaction model",
}

@Article{ElAbbadi:2001:GE,
  author =       "Amr {El Abbadi} and Gunter Schlageter and Kyu-Young
                 Whang",
  title =        "Guest editorial",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "2--3",
  pages =        "119--119",
  month =        sep,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100053",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:58 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010002/10100119.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010002/10100119.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Pucheral:2001:PSD,
  author =       "Philippe Pucheral and Luc Bouganim and Patrick
                 Valduriez and Christophe Bobineau",
  title =        "{PicoDBMS}: {Scaling} down database techniques for the
                 smartcard",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "2--3",
  pages =        "120--132",
  month =        sep,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100047",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:58 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010002/10100120.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010002/10100120.pdf",
  abstract =     "Smartcards are the most secure portable computing
                 device today. They have been used successfully in
                 applications involving money, and proprietary and
                 personal data (such as banking, healthcare, insurance,
                 etc.). As smartcards get more powerful (with 32-bit CPU
                 and more than 1 MB of stable memory in the next
                 versions) and become multi-application, the need for
                 database management arises. However, smartcards have
                 severe hardware limitations (very slow write, very
                 little RAM, constrained stable memory, no autonomy,
                 etc.) which make traditional database technology
                 irrelevant. The major problem is scaling down database
                 techniques so they perform well under these
                 limitations. In this paper, we give an in-depth
                 analysis of this problem and propose a PicoDBMS
                 solution based on highly compact data structures, query
                 execution without RAM, and specific techniques for
                 atomicity and durability. We show the effectiveness of
                 our techniques through performance evaluation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "atomicity; durability; execution model; PicoDBMS;
                 query optimization; smartcard applications; storage
                 model",
}

@Article{Shanmugasundaram:2001:EPR,
  author =       "Jayavel Shanmugasundaram and Eugene Shekita and Rimon
                 Barr and Michael Carey and Bruce Lindsay and Hamid
                 Pirahesh and Berthold Reinwald",
  title =        "Efficiently publishing relational data as {XML}
                 documents",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "2--3",
  pages =        "133--154",
  month =        sep,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100052",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:58 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010002/10100133.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010002/10100133.pdf",
  abstract =     "XML is rapidly emerging as a standard for exchanging
                 business data on the World Wide Web. For the
                 foreseeable future, however, most business data will
                 continue to be stored in relational database systems.
                 Consequently, if XML is to fulfill its potential, some
                 mechanism is needed to publish relational data as XML
                 documents. Towards that goal, one of the major
                 challenges is finding a way to efficiently structure
                 and tag data from one or more tables as a hierarchical
                 XML document. Different alternatives are possible
                 depending on when this processing takes place and how
                 much of it is done inside the relational engine. In
                 this paper, we characterize and study the performance
                 of these alternatives. Among other things, we explore
                 the use of new scalar and aggregate functions in SQL
                 for constructing complex XML documents directly in the
                 relational engine. We also explore different execution
                 plans for generating the content of an XML document.
                 The results of an experimental study show that
                 constructing XML documents inside the relational engine
                 can have a significant performance benefit. Our results
                 also show the superiority of having the relational
                 engine use what we call an ``outer union plan'' to
                 generate the content of an XML document.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "publishing; relational databases; XML",
}

@Article{Chang:2001:AQM,
  author =       "Kevin Chen-Chuan Chang and H{\'e}ctor
                 Garc{\'\i}a-Molina",
  title =        "Approximate query mapping: {Accounting} for
                 translation closeness",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "2--3",
  pages =        "155--181",
  month =        sep,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100042",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:58 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010002/10100155.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010002/10100155.pdf",
  abstract =     "In this paper we present a mechanism for approximately
                 translating Boolean query constraints across
                 heterogeneous information sources. Achieving the best
                 translation is challenging because sources support
                 different constraints for formulating queries, and
                 often these constraints cannot be precisely translated.
                 For instance, a query [score>8] might be ``perfectly''
                 translated as [rating>0.8] at some site, but can only
                 be approximated as [grade=A] at another. Unlike other
                 work, our general framework adopts a customizable
                 ``closeness'' metric for the translation that combines
                 both precision and recall. Our results show that for
                 query translation we need to handle interdependencies
                 among both query conjuncts as well as disjuncts. As the
                 basis, we identify the essential requirements of a rule
                 system for users to encode the mappings for atomic
                 semantic units. Our algorithm then translates complex
                 queries by rewriting them in terms of the semantic
                 units. We show that, under practical assumptions, our
                 algorithm generates the best approximate translations
                 with respect to the closeness metric of choice. We also
                 present a case study to show how our technique may be
                 applied in practice.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "approximate query translation; closeness;
                 constraint-mapping; information integration;
                 mediators",
}

@Article{Pottinger:2001:MSA,
  author =       "Rachel Pottinger and Alon Halevy",
  title =        "{MiniCon}: {A} scalable algorithm for answering
                 queries using views",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "2--3",
  pages =        "182--198",
  month =        sep,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100048",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:58 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010002/10100182.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010002/10100182.pdf",
  abstract =     "The problem of answering queries using views is to
                 find efficient methods of answering a query using a set
                 of previously materialized views over the database,
                 rather than accessing the database relations. The
                 problem has received significant attention because of
                 its relevance to a wide variety of data management
                 problems, such as data integration, query optimization,
                 and the maintenance of physical data independence. To
                 date, the performance of proposed algorithms has
                 received very little attention, and in particular,
                 their scale up in the presence of a large number of
                 views is unknown. We first analyze two previous
                 algorithms, the bucket algorithm and the inverse-rules,
                 and show their deficiencies. We then describe the
                 MiniCon, a novel algorithm for finding the
                 maximally-contained rewriting of a conjunctive query
                 using a set of conjunctive views. We present the first
                 experimental study of algorithms for answering queries
                 using views. The study shows that the MiniCon scales up
                 well and significantly outperforms the previous
                 algorithms. We describe an extension of the MiniCon to
                 handle comparison predicates, and show its performance
                 experimentally. Finally, we describe how the MiniCon
                 can be extended to the context of query optimization.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data integration; materialized views; query
                 optimization; Web and databases",
}

@Article{Chakrabarti:2001:AQP,
  author =       "Kaushik Chakrabarti and Minos Garofalakis and Rajeev
                 Rastogi and Kyuseok Shim",
  title =        "Approximate query processing using wavelets",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "2--3",
  pages =        "199--223",
  month =        sep,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100049",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:58 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010002/10100199.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010002/10100199.pdf",
  abstract =     "Approximate query processing has emerged as a
                 cost-effective approach for dealing with the huge data
                 volumes and stringent response-time requirements of
                 today's decision support systems (DSS). Most work in
                 this area, however, has so far been limited in its
                 query processing scope, typically focusing on specific
                 forms of aggregate queries. Furthermore, conventional
                 approaches based on sampling or histograms appear to be
                 inherently limited when it comes to approximating the
                 results of complex queries over high-dimensional DSS
                 data sets. In this paper, we propose the use of
                 multi-dimensional wavelets as an effective tool for
                 general-purpose approximate query processing in modern,
                 high-dimensional applications. Our approach is based on
                 building {\em wavelet-coefficient synopses\/} of the
                 data and using these synopses to provide approximate
                 answers to queries. We develop novel query processing
                 algorithms that operate directly on the
                 wavelet-coefficient synopses of relational tables,
                 allowing us to process arbitrarily complex queries {\em
                 entirely\/} in the wavelet-coefficient domain. This
                 guarantees extremely fast response times since our
                 approximate query execution engine can do the bulk of
                 its processing over compact sets of wavelet
                 coefficients, essentially postponing the expansion into
                 relational tuples until the end-result of the query. We
                 also propose a novel wavelet decomposition algorithm
                 that can build these synopses in an I/O-efficient
                 manner. Finally, we conduct an extensive experimental
                 study with synthetic as well as real-life data sets to
                 determine the effectiveness of our wavelet-based
                 approach compared to sampling and histograms. Our
                 results demonstrate that our techniques: (1) provide
                 approximate answers of better quality than either
                 sampling or histograms; (2) offer query execution-time
                 speedups of more than two orders of magnitude; and (3)
                 guarantee extremely fast synopsis construction times
                 that scale linearly with the size of the data.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "approximate query answers; data synopses; query
                 processing; wavelet decomposition",
}

@Article{Sarawagi:2001:UCM,
  author =       "Sunita Sarawagi",
  title =        "User-cognizant multidimensional analysis",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "2--3",
  pages =        "224--239",
  month =        sep,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100046",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:58 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010002/10100224.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010002/10100224.pdf",
  abstract =     "Our goal is to enhance multidimensional database
                 systems with a suite of advanced operators to automate
                 data analysis tasks that are currently handled through
                 manual exploration. In this paper, we present a key
                 component of our system that characterizes the
                 information content of a cell based on a user's prior
                 familiarity with the cube and provides a
                 context-sensitive exploration of the cube. There are
                 three main modules of this component. A Tracker, that
                 continuously tracks the parts of the cube that a user
                 has visited. A Modeler, that pieces together the
                 information in the visited parts to model the user's
                 expected values in the unvisited parts. An Informer,
                 that processes user's queries about the most
                 informative unvisited parts of the cube. The
                 mathematical basis for the expected value modeling is
                 provided by the classical maximum entropy principle.
                 Accordingly, the expected values are computed so as to
                 agree with every value that is already visited while
                 reducing assumptions about unvisited values to the
                 minimum by maximizing their entropy. The most
                 informative values are defined as those that bring the
                 new expected values closest to the actual values. We
                 believe and prove through experiments that such a
                 user-in-the-loop exploration will enable much faster
                 assimilation of all significant information in the data
                 compared to existing manual explorations.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "maximum entropy; multidimensional data exploration;
                 OLAP; personalized mining; user-sensitive interest
                 measure",
}

@Article{Turker:2001:SIS,
  author =       "Can T{\"u}rker and Michael Gertz",
  title =        "Semantic integrity support in {SQL:1999} and
                 commercial (object-)relational database management
                 systems",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "4",
  pages =        "241--269",
  month =        dec,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100050",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:59 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010004/10100241.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010004/10100241.pdf",
  abstract =     "The correctness of the data managed by database
                 systems is vital to any application that utilizes data
                 for business, research, and decision-making purposes.
                 To guard databases against erroneous data not
                 reflecting real-world data or business rules, semantic
                 integrity constraints can be specified during database
                 design. Current commercial database management systems
                 provide various means to implement mechanisms to
                 enforce semantic integrity constraints at database
                 run-time. In this paper, we give an overview of the
                 semantic integrity support in the most recent
                 SQL-standard SQL:1999, and we show to what extent the
                 different concepts and language constructs proposed in
                 this standard can be found in major commercial
                 (object-)relational database management systems. In
                 addition, we discuss general design guidelines that
                 point out how the semantic integrity features provided
                 by these systems should be utilized in order to
                 implement an effective integrity enforcing subsystem
                 for a database.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "constraint enforcement; object-relational databases;
                 semantic integrity constraints; SQL:1999",
}

@Article{Halevy:2001:AQU,
  author =       "Alon Y. Halevy",
  title =        "Answering queries using views: {A} survey",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "4",
  pages =        "270--294",
  month =        dec,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100054",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:59 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010004/10100270.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010004/10100270.pdf",
  abstract =     "The problem of answering queries using views is to
                 find efficient methods of answering a query using a set
                 of previously defined materialized views over the
                 database, rather than accessing the database relations.
                 The problem has recently received significant attention
                 because of its relevance to a wide variety of data
                 management problems. In query optimization, finding a
                 rewriting of a query using a set of materialized views
                 can yield a more efficient query execution plan. To
                 support the separation of the logical and physical
                 views of data, a storage schema can be described using
                 views over the logical schema. As a result, finding a
                 query execution plan that accesses the storage amounts
                 to solving the problem of answering queries using
                 views. Finally, the problem arises in data integration
                 systems, where data sources can be described as
                 precomputed views over a mediated schema. This article
                 surveys the state of the art on the problem of
                 answering queries using views, and synthesizes the
                 disparate works into a coherent framework. We describe
                 the different applications of the problem, the
                 algorithms proposed to solve it and the relevant
                 theoretical results.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data integration; date warehousing; materialized
                 views; query optimization; survey; Web-site
                 management",
}

@Article{Laurent:2001:MCI,
  author =       "D. Laurent and J. Lechtenb{\"o}rger and N. Spyratos
                 and G. Vossen",
  title =        "Monotonic complements for independent data
                 warehouses",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "4",
  pages =        "295--315",
  month =        dec,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100055",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:59 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010004/10100295.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010004/10100295.pdf",
  abstract =     "Views over databases have regained attention in the
                 context of data warehouses, which are seen as {\em
                 materialized\/} views. In this setting, efficient view
                 maintenance is an important issue, for which the notion
                 of {\em self-maintainability\/} has been identified as
                 desirable. In this paper, we extend the concept of
                 self-maintainability to (query and update) {\em
                 independence\/} within a formal framework, where
                 independence with respect to arbitrary given sets of
                 queries and updates over the sources can be guaranteed.
                 To this end we establish an intuitively appealing
                 connection between warehouse independence and {\em view
                 complements}. Moreover, we study special kinds of
                 complements, namely {\em monotonic complements}, and
                 show how to compute minimal ones in the presence of
                 keys and foreign keys in the underlying databases.
                 Taking advantage of these complements, an algorithmic
                 approach is proposed for the specification of
                 independent warehouses with respect to given sets of
                 queries and updates.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data warehouse; independence; materialized view;
                 self-maintainability; view complement",
}

@Article{Grefen:2001:GTS,
  author =       "Paul Grefen and Jochem Vonk and Peter Apers",
  title =        "Global transaction support for workflow management
                 systems: from formal specification to practical
                 implementation",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "4",
  pages =        "316--333",
  month =        dec,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100056",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:59 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010004/10100316.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010004/10100316.pdf",
  abstract =     "In this paper, we present an approach to global
                 transaction management in workflow environments. The
                 transaction mechanism is based on the well-known notion
                 of compensation, but extended to deal with both
                 arbitrary process structures to allow cycles in
                 processes and safepoints to allow partial compensation
                 of processes. We present a formal specification of the
                 transaction model and transaction management algorithms
                 in set and graph theory, providing clear, unambiguous
                 transaction semantics. The specification is
                 straightforwardly mapped to a modular architecture, the
                 implementation of which is first applied in a testing
                 environment, then in the prototype of a commercial
                 workflow management system. The modular nature of the
                 resulting system allows easy distribution using
                 middleware technology. The path from abstract semantics
                 specification to concrete, real-world implementation of
                 a workflow transaction mechanism is thus covered in a
                 complete and coherent fashion. As such, this paper
                 provides a complete framework for the application of
                 well-founded transactional workflows.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "compensation; long-running transaction; transaction
                 management; workflow management",
}

@Article{Rahm:2001:SAA,
  author =       "Erhard Rahm and Philip A. Bernstein",
  title =        "A survey of approaches to automatic schema matching",
  journal =      j-VLDB-J,
  volume =       "10",
  number =       "4",
  pages =        "334--350",
  month =        dec,
  year =         "2001",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100057",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:50:59 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t1010004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/1010004/10100334.htm;
                 http://link.springer.de/link/service/journals/00778/papers/1010004/10100334.pdf",
  abstract =     "Schema matching is a basic problem in many database
                 application domains, such as data integration,
                 E-business, data warehousing, and semantic query
                 processing. In current implementations, schema matching
                 is typically performed manually, which has significant
                 limitations. On the other hand, previous research
                 papers have proposed many techniques to achieve a
                 partial automation of the match operation for specific
                 application domains. We present a taxonomy that covers
                 many of these existing approaches, and we describe the
                 approaches in some detail. In particular, we
                 distinguish between schema-level and instance-level,
                 element-level and structure-level, and language-based
                 and constraint-based matchers. Based on our
                 classification we review some previous match
                 implementations thereby indicating which part of the
                 solution space they cover. We intend our taxonomy and
                 review of past work to be useful when comparing
                 different approaches to schema matching, when
                 developing a new match algorithm, and when implementing
                 a schema matching component.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "graph matching; machine learning; model management;
                 schema integration; schema matching",
}

@Article{Saltenis:2002:INR,
  author =       "Simonas {\v{S}}altenis and Christian S. Jensen",
  title =        "Indexing of now-relative spatio-bitemporal data",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "1",
  pages =        "1--16",
  month =        aug,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100058",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:00 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011001/20110001.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011001/20110001.pdf",
  abstract =     "Real-world entities are inherently spatially and
                 temporally referenced, and database applications
                 increasingly exploit databases that record the past,
                 present, and anticipated future locations of entities,
                 e.g., the residences of customers obtained by the
                 geo-coding of addresses. Indices that efficiently
                 support queries on the spatio-temporal extents of such
                 entities are needed. However, past indexing research
                 has progressed in largely separate spatial and temporal
                 streams. Adding time dimensions to spatial indices, as
                 if time were a spatial dimension, neither supports nor
                 exploits the special properties of time. On the other
                 hand, temporal indices are generally not amenable to
                 extension with spatial dimensions. This paper proposes
                 the first efficient and versatile index for a general
                 class of spatio-temporal data: the discretely changing
                 spatial aspect of an object may be a point or may have
                 an extent; both transaction time and valid time are
                 supported, and a generalized notion of the current
                 time, {\em now}, is accommodated for both temporal
                 dimensions. The index is based on the R$^*$-tree and
                 provides means of prioritizing space versus time, which
                 enables it to adapt to spatially and temporally
                 restrictive queries. Performance experiments are
                 reported that evaluate pertinent aspects of the
                 index.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access method; bitemporal data; multidimensional
                 indexing; R-tree; spatio-temporal data; transaction
                 time; valid time",
}

@Article{Rafiei:2002:ERS,
  author =       "Davood Rafiei and Alberto O. Mendelzon",
  title =        "Efficient retrieval of similar shapes",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "1",
  pages =        "17--27",
  month =        aug,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780100059",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:00 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011001/20110017.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011001/20110017.pdf",
  abstract =     "We propose an indexing technique for the fast
                 retrieval of objects in 2D images based on similarity
                 between their boundary shapes. Our technique is robust
                 in the presence of noise and supports several important
                 notions of similarity including optimal matches
                 irrespective of variations in orientation and/or
                 position. Our method can also handle size-invariant
                 matches using a normalization technique, although
                 optimality is not guaranteed here. We implemented our
                 method and performed experiments on real (hand-written
                 digits) data. Our experimental results showed the
                 superiority of our method compared to search based on
                 sequential scanning, which is the only obvious
                 competitor. The performance gain of our method
                 increases with any increase in the number or the size
                 of shapes.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "Fourier descriptors; image databases; shape retrieval;
                 similarity queries; similarity retrieval",
}

@Article{Navarro:2002:SMS,
  author =       "Gonzalo Navarro",
  title =        "Searching in metric spaces by spatial approximation",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "1",
  pages =        "28--46",
  month =        aug,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780200060",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:00 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011001/20110028.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011001/20110028.pdf",
  abstract =     "We propose a new data structure to search in metric
                 spaces. A {\em metric space\/} is formed by a
                 collection of objects and a {\em distance function\/}
                 defined among them which satisfies the triangle
                 inequality. The goal is, given a set of objects and a
                 query, retrieve those objects close enough to the
                 query. The complexity measure is the number of
                 distances computed to achieve this goal. Our data
                 structure, called {\em sa-tree\/} (``spatial
                 approximation tree''), is based on approaching the
                 searched objects spatially, that is, getting closer and
                 closer to them, rather than the classic
                 divide-and-conquer approach of other data structures.
                 We analyze our method and show that the number of
                 distance evaluations to search among $n$ objects is
                 sublinear. We show experimentally that the {\em
                 sa-tree\/} is the best existing technique when the
                 metric space is hard to search or the query has low
                 selectivity. These are the most important unsolved
                 cases in real applications. As a practical advantage,
                 our data structure is one of the few that does not need
                 to tune parameters, which makes it appealing for use by
                 non-experts.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "multimedia databases; similarity or proximity search;
                 spatial and multidimensional search; spatial
                 approximation tree",
}

@Article{Mihaila:2002:LAD,
  author =       "George A. Mihaila and Louiqa Raschid and Anthony
                 Tomasic",
  title =        "Locating and accessing data repositories with
                 {WebSemantics}",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "1",
  pages =        "47--57",
  month =        aug,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780200061",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:00 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011001/20110047.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011001/20110047.pdf",
  abstract =     "Many collections of scientific data in particular
                 disciplines are available today on the World Wide Web.
                 Most of these data sources are compliant with some
                 standard for interoperable access. In addition, sources
                 may support a common semantics, i.e., a shared meaning
                 for the data types and their domains. However, sharing
                 data among a global community of users is still
                 difficult because of the following reasons: (i) data
                 providers need a mechanism for describing and
                 publishing available sources of data; (ii) data
                 administrators need a mechanism for discovering the
                 location of published sources and obtaining metadata
                 from these sources; and (iii) users need a mechanism
                 for browsing and selecting sources. This paper
                 describes a system, WebSemantics, that accomplishes the
                 above tasks. We describe an architecture for the
                 publication and discovery of scientific data sources,
                 which is an extension of the World Wide Web
                 architecture and protocols. We support catalogs
                 containing metadata about data sources for some
                 application domain. We define a language for
                 discovering sources and querying their metadata. We
                 then describe the WebSemantics prototype.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data discovery; data integration; mediators; query
                 languages; World Wide Web; XML",
}

@Article{Ferrari:2002:ASD,
  author =       "E. Ferrari and N. R. Adam and V. Atluri and E. Bertino
                 and U. Capuozzo",
  title =        "An authorization system for digital libraries",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "1",
  pages =        "58--67",
  month =        aug,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780200063",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:00 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011001/20110058.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011001/20110058.pdf",
  abstract =     "Digital Libraries (DLs) introduce several challenging
                 requirements with respect to the formulation,
                 specification, and enforcement of adequate data
                 protection policies. Unlike conventional database
                 environments, a DL environment typically is
                 characterized by a dynamic subject population, often
                 making accesses from remote locations, and by an
                 extraordinarily large amount of multimedia information,
                 stored in a variety of formats. Moreover, in a DL
                 environment, access policies are often specified based
                 on subject qualifications and characteristics, rather
                 than subject identity. Traditional authorization models
                 are not adequate to meet access control requirements of
                 DLs. In this paper, we present a {\em Digital Library
                 Authorization System\/} (DLAS). DLAS employs a
                 content-based authorization model, called a {\em
                 Digital Library Authorization Model\/} (DLAM) which was
                 proposed in previous work [1].",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access control; credentials; digital libraries",
}

@Article{Marathe:2002:QPT,
  author =       "Arunprasad P. Marathe and Kenneth Salem",
  title =        "Query processing techniques for arrays",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "1",
  pages =        "68--91",
  month =        aug,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780200062",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:00 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011001/20110068.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011001/20110068.pdf",
  abstract =     "Arrays are a common and important class of data. At
                 present, database systems do not provide adequate array
                 support: arrays can neither be easily defined nor
                 conveniently manipulated. Further, array manipulations
                 are not optimized. This paper describes a language
                 called the {\em Array Manipulation Language\/} (AML),
                 for expressing array manipulations, and a collection of
                 optimization techniques for AML expressions. In the AML
                 framework for array manipulation, arbitrary
                 externally-defined functions can be applied to arrays
                 in a structured manner. AML can be adapted to different
                 application domains by choosing appropriate external
                 function definitions. This paper concentrates on arrays
                 occurring in databases of digital images such as
                 satellite or medical images. AML queries can be treated
                 declaratively and subjected to rewrite optimizations.
                 Rewriting minimizes the number of applications of
                 potentially costly external functions required to
                 compute a query result. AML queries can also be
                 optimized for space. Query results are generated a
                 piece at a time by pipelined execution plans, and the
                 amount of memory required by a plan depends on the
                 order in which pieces are generated. An optimizer can
                 consider generating the pieces of the query result in a
                 variety of orders, and can efficiently choose orders
                 that require less space. An AML-based prototype array
                 database system called {\em ArrayDB\/} has been built,
                 and it is used to show the effectiveness of these
                 optimization techniques.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "array manipulation language; array query optimization;
                 declarative query language; memory-usage optimization;
                 pipelined evaluation; user-defined functions",
}

@Article{Sakurai:2002:SIH,
  author =       "Yasushi Sakurai and Masatoshi Yoshikawa and Shunsuke
                 Uemura and Haruhiko Kojima",
  title =        "Spatial indexing of high-dimensional data based on
                 relative approximation",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "2",
  pages =        "93--108",
  month =        oct,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0066-9",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:01 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011002/20110093.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011002/20110093.pdf",
  abstract =     "We propose a novel index structure, the A-tree
                 (approximation tree), for similarity searches in
                 high-dimensional data. The basic idea of the A-tree is
                 the introduction of virtual bounding rectangles (VBRs)
                 which contain and approximate MBRs or data objects.
                 VBRs can be represented quite compactly and thus affect
                 the tree configuration both quantitatively and
                 qualitatively. First, since tree nodes can contain a
                 large number of VBR entries, fanout becomes large,
                 which increases search speed. More importantly, we have
                 a free hand in arranging MBRs and VBRs in the tree
                 nodes. Each A-tree node contains an MBR and its
                 children VBRs. Therefore, by fetching an A-tree node,
                 we can obtain information on the exact position of a
                 parent MBR and the approximate position of its
                 children. We have performed experiments using both
                 synthetic and real data sets. For the real data sets,
                 the A-tree outperforms the SR-tree and the VA-file in
                 all dimensionalities up to 64 dimensions, which is the
                 highest dimension in our experiments. Additionally, we
                 propose a cost model for the A-tree. We verify the
                 validity of the cost model for synthetic and real data
                 sets.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "high-dimensional data; relative approximation;
                 similarity search",
}

@Article{Hjaltason:2002:SCP,
  author =       "Gisli R. Hjaltason and Hanan Samet",
  title =        "Speeding up construction of {PMR} quadtree-based
                 spatial indexes",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "2",
  pages =        "109--137",
  month =        oct,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0067-8",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:01 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011002/20110109.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011002/20110109.pdf",
  abstract =     "Spatial indexes, such as those based on the quadtree,
                 are important in spatial databases for efficient
                 execution of queries involving spatial constraints,
                 especially when the queries involve spatial joins. In
                 this paper we present a number of techniques for
                 speeding up the construction of quadtree-based spatial
                 indexes, specifically the PMR quadtree, which can index
                 arbitrary spatial data. We assume a quadtree
                 implementation using the ``linear quadtree'', a
                 disk-resident representation that stores objects
                 contained in the leaf nodes of the quadtree in a linear
                 index (e.g., a B-tree) ordered based on a space-filling
                 curve. We present two complementary techniques: an
                 improved insertion algorithm and a bulk-loading method.
                 The bulk-loading method can be extended to handle
                 bulk-insertions into an existing PMR quadtree. We make
                 some analytical observations about the I/O cost and CPU
                 cost of our PMR quadtree bulk-loading algorithm, and
                 conduct an extensive empirical study of the techniques
                 presented in the paper. Our techniques are found to
                 yield significant speedup compared to traditional
                 quadtree building methods, even when the size of a main
                 memory buffer is very small compared to the size of the
                 resulting quadtrees.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "bulk-loading; I/O; spatial indexing",
}

@Article{Nanopoulos:2002:ESS,
  author =       "Alexandros Nanopoulos and Yannis Manolopoulos",
  title =        "Efficient similarity search for market basket data",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "2",
  pages =        "138--152",
  month =        oct,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0068-7",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:01 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011002/20110138.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011002/20110138.pdf",
  abstract =     "Several organizations have developed very large market
                 basket databases for the maintenance of customer
                 transactions. New applications, e.g., Web
                 recommendation systems, present the requirement for
                 processing similarity queries in market basket
                 databases. In this paper, we propose a novel scheme for
                 similarity search queries in basket data. We develop a
                 new representation method, which, in contrast to
                 existing approaches, is proven to provide correct
                 results. New algorithms are proposed for the processing
                 of similarity queries. Extensive experimental results,
                 for a variety of factors, illustrate the superiority of
                 the proposed scheme over the state-of-the-art method.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data mining; market basket data; nearest-neighbor;
                 similarity search",
}

@Article{Feng:2002:TMM,
  author =       "Ling Feng and Jeffrey Xu Yu and Hongjun Lu and Jiawei
                 Han",
  title =        "A template model for multidimensional
                 inter-transactional association rules",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "2",
  pages =        "153--175",
  month =        oct,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0069-6",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:01 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011002.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011002/20110153.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011002/20110153.pdf",
  abstract =     "Multidimensional inter-transactional association rules
                 extend the traditional association rules to describe
                 more general associations among items with multiple
                 properties across transactions. `` {\em After McDonald
                 and Burger King open branches, KFC will open a branch
                 two months later and one mile away}'' is an example of
                 such rules. Since the number of potential
                 inter-transactional association rules tends to be
                 extremely large, mining inter-transactional
                 associations poses more challenges on efficient
                 processing than mining traditional intra-transactional
                 associations. In order to make such association rule
                 mining truly practical and computationally tractable,
                 in this study we present a template model to help users
                 declare the interesting {\em multidimensional
                 inter-transactional associations\/} to be mined. With
                 the guidance of templates, several optimization
                 techniques, i.e., joining, converging, and speeding,
                 are devised to speed up the discovery of
                 inter-transactional association rules. We show, through
                 a series of experiments on both synthetic and real-life
                 data sets, that these optimization techniques can yield
                 significant performance benefits.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "intra-transactional/inter-transactional association
                 rules; multidimensional context; template model",
}

@Article{Apers:2002:E,
  author =       "Peter Apers and Stefano Ceri and Richard Snodgrass",
  title =        "Editorial",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "3",
  pages =        "177--178",
  month =        nov,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0075-8",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:02 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Special issue VLDB best papers 2001.",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011003/20110177.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011003/20110177.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{An:2002:EPT,
  author =       "Ning An and Sudhanva Gurumurthi and Anand
                 Sivasubramaniam and Narayanan Vijaykrishnan and Mahmut
                 Kandemir and Mary Jane Irwin",
  title =        "Energy-performance trade-offs for spatial access
                 methods on memory-resident data",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "3",
  pages =        "179--197",
  month =        nov,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0073-x",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:02 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Special issue VLDB best papers 2001.",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011003/20110179.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011003/20110179.pdf",
  abstract =     "The proliferation of mobile and pervasive computing
                 devices has brought energy constraints into the
                 limelight. Energy-conscious design is important at all
                 levels of system architecture, and the software has a
                 key role to play in conserving battery energy on these
                 devices. With the increasing popularity of spatial
                 database applications, and their anticipated deployment
                 on mobile devices (such as road atlases and GPS-based
                 applications), it is critical to examine the energy
                 implications of spatial data storage and access methods
                 for memory resident datasets. While there has been
                 extensive prior research on spatial access methods on
                 resource-rich environments, this is, perhaps, the first
                 study to examine their suitability for
                 resource-constrained environments. Using a detailed
                 cycle-accurate energy estimation framework and four
                 different datasets, this paper examines the pros and
                 cons of three previously proposed spatial indexing
                 alternatives from both the energy and performance
                 angles. Specifically, the Quadtree, Packed R-tree, and
                 Buddy-Tree structures are evaluated and compared with a
                 brute-force approach that does not use an index. The
                 results show that there are both performance and energy
                 trade-offs between the indexing schemes for the
                 different queries. The nature of the query also plays
                 an important role in determining the energy-performance
                 trade-offs. Further, technological trends and
                 architectural enhancements are influencing factors on
                 the relative behavior of the index structures. The work
                 in the query has a bearing on how and where (on a
                 mobile client or/and on a server) it should be
                 performed for performance and energy savings. The
                 results from this study will be beneficial for the
                 design and implementation of embedded spatial
                 databases, accelerating their deployment on numerous
                 mobile devices.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "energy optimization; multidimensional indexing;
                 resource-constrained computing; spatial data",
}

@Article{Ailamaki:2002:DPL,
  author =       "Anastassia Ailamaki and David J. DeWitt and Mark D.
                 Hill",
  title =        "Data page layouts for relational databases on deep
                 memory hierarchies",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "3",
  pages =        "198--215",
  month =        nov,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0074-9",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:02 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Special issue VLDB best papers 2001.",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011003/20110198.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011003/20110198.pdf",
  abstract =     "Relational database systems have traditionally
                 optimized for I/O performance and organized records
                 sequentially on disk pages using the N-ary Storage
                 Model (NSM) (a.k.a., slotted pages). Recent research,
                 however, indicates that cache utilization and
                 performance is becoming increasingly important on
                 modern platforms. In this paper, we first demonstrate
                 that in-page data placement is the key to high cache
                 performance and that NSM exhibits low cache utilization
                 on modern platforms. Next, we propose a new data
                 organization model called PAX (Partition Attributes
                 Across), that significantly improves cache performance
                 by grouping together all values of each attribute
                 within each page. Because PAX only affects layout
                 inside the pages, it incurs no storage penalty and does
                 not affect I/O behavior. According to our experimental
                 results (which were obtained without using any indices
                 on the participating relations), when compared to NSM:
                 (a) PAX exhibits superior cache and memory bandwidth
                 utilization, saving at least 75\% of NSM's stall time
                 due to data cache accesses; (b) range selection queries
                 and updates on memory-resident relations execute 1725\%
                 faster; and (c) TPC-H queries involving I/O execute
                 1148\% faster. Finally, we show that PAX performs well
                 across different memory system designs.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "cache-conscious database systems; disk page layout;
                 relational data placement",
}

@Article{Chirkova:2002:FPV,
  author =       "Rada Chirkova and Alon Y. Halevy and Dan Suciu",
  title =        "A formal perspective on the view selection problem",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "3",
  pages =        "216--237",
  month =        nov,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0070-0",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:02 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Special issue VLDB best papers 2001.",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011003/20110216.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011003/20110216.pdf",
  abstract =     "The view selection problem is to choose a set of views
                 to materialize over a database schema, such that the
                 cost of evaluating a set of workload queries is
                 minimized and such that the views fit into a
                 prespecified storage constraint. The two main
                 applications of the view selection problem are
                 materializing views in a database to speed up query
                 processing, and selecting views to materialize in a
                 data warehouse to answer decision support queries. In
                 addition, view selection is a core problem for
                 intelligent data placement over a wide-area network for
                 data integration applications and data management for
                 ubiquitous computing. We describe several fundamental
                 results concerning the view selection problem. We
                 consider the problem for views and workloads that
                 consist of equality-selection, project and join
                 queries, and show that the complexity of the problem
                 depends crucially on the quality of the estimates that
                 a query optimizer has on the size of the views it is
                 considering to materialize. When a query optimizer has
                 good estimates of the sizes of the views, we show a
                 somewhat surprising result, namely, that an optimal
                 choice of views may involve a number of views that is
                 exponential in the size of the database schema. On the
                 other hand, when an optimizer uses standard estimation
                 heuristics, we show that the number of necessary views
                 and the expression size of each view are polynomially
                 bounded.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "materialized views; view selection",
}

@Article{Aguilera:2002:VLS,
  author =       "Vincent Aguilera and Sophie Cluet and Tova Milo and
                 Pierangelo Veltri and Dan Vodislav",
  title =        "Views in a large-scale {XML} repository",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "3",
  pages =        "238--255",
  month =        nov,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0065-x",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:02 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Special issue VLDB best papers 2001.",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011003/20110238.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011003/20110238.pdf",
  abstract =     "We are interested in defining and querying views in a
                 huge and highly heterogeneous XML repository (Web
                 scale). In this context, view definitions are very
                 large, involving lots of sources, and there is no
                 apparent limitation to their size. This raises
                 interesting problems that we address in the paper: (i)
                 how to distribute views over several machines without
                 having a negative impact on the query translation
                 process; (ii) how to quickly select the relevant part
                 of a view given a query; (iii) how to minimize the cost
                 of communicating potentially large queries to the
                 machines where they will be evaluated. The solution
                 that we propose is based on a simple view definition
                 language that allows for automatic generation of views.
                 The language maps paths in the view abstract DTD to
                 paths in the concrete source DTDs. It enables a
                 distributed implementation of the view system that is
                 scalable both in terms of data and load. In particular,
                 the query translation algorithm is shown to have a good
                 (linear) complexity.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "query evaluation; semantic integration; views;
                 warehouse; XML",
}

@Article{Hunt:2002:DIL,
  author =       "Ela Hunt and Malcolm P. Atkinson and Robert W.
                 Irving",
  title =        "Database indexing for large {DNA} and protein sequence
                 collections",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "3",
  pages =        "256--271",
  month =        nov,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s007780200064",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:02 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011003.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  note =         "Special issue VLDB best papers 2001.",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011003/20110256.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011003/20110256.pdf",
  abstract =     "Our aim is to develop new database technologies for
                 the approximate matching of unstructured string data
                 using indexes. We explore the potential of the suffix
                 tree data structure in this context. We present a new
                 method of building suffix trees, allowing us to build
                 trees in excess of RAM size, which has hitherto not
                 been possible. We show that this method performs in
                 practice as well as the $O(n)$ method of Ukkonen [70].
                 Using this method we build indexes for 200 Mb of
                 protein and 300 Mbp of DNA, whose disk-image exceeds
                 the available RAM. We show experimentally that suffix
                 trees can be effectively used in approximate string
                 matching with biological data. For a range of query
                 lengths and error bounds the suffix tree reduces the
                 size of the unoptimised $O(mn)$ dynamic programming
                 calculation required in the evaluation of string
                 similarity, and the gain from indexing increases with
                 index size. In the indexes we built this reduction is
                 significant, and less than 0.3\% of the expected matrix
                 is evaluated. We detail the requirements for further
                 database and algorithmic research to support efficient
                 use of large suffix indexes in biological
                 applications.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "approximate matching; biological sequence; database
                 index; suffix tree",
}

@Article{Halevy:2002:GE,
  author =       "Alon Y. Halevy",
  title =        "Guest Editorial",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "4",
  pages =        "273--273",
  month =        dec,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0082-9",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:03 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011004/20110273.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011004/20110273.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Jagadish:2002:TNX,
  author =       "H. V. Jagadish and S. Al-Khalifa and A. Chapman and L.
                 V. S. Lakshmanan and A. Nierman and S. Paparizos and
                 J. M. Patel and D. Srivastava and N. Wiwatwattana and
                 Y. Wu and C. Yu",
  title =        "{TIMBER}: {A} native {XML} database",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "4",
  pages =        "274--291",
  month =        dec,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0081-x",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:03 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011004/20110274.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011004/20110274.pdf",
  abstract =     "This paper describes the overall design and
                 architecture of the Timber XML database system
                 currently being implemented at the University of
                 Michigan. The system is based upon a bulk algebra for
                 manipulating trees, and natively stores XML. New access
                 methods have been developed to evaluate queries in the
                 XML context, and new cost estimation and query
                 optimization techniques have also been developed. We
                 present performance numbers to support some of our
                 design decisions. We believe that the key intellectual
                 contribution of this system is a comprehensive
                 set-at-a-time query processing ability in a native XML
                 store, with all the standard components of relational
                 query processing, including algebraic rewriting and a
                 cost-based optimizer.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "algebra; document management; hierarchical; query
                 processing; semi-structured",
}

@Article{Fiebig:2002:ANX,
  author =       "T. Fiebig and S. Helmer and C.-C. Kanne and G.
                 Moerkotte and J. Neumann and R. Schiele and T. Westmann",
  title =        "Anatomy of a native {XML} base management system",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "4",
  pages =        "292--314",
  month =        dec,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0080-y",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:03 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011004/20110292.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011004/20110292.pdf",
  abstract =     "Several alternatives to manage large XML document
                 collections exist, ranging from file systems over
                 relational or other database systems to specifically
                 tailored XML base management systems. In this paper we
                 give a tour of Natix, a database management system
                 designed from scratch for storing and processing XML
                 data. Contrary to the common belief that management of
                 XML data is just another application for traditional
                 databases like relational systems, we illustrate how
                 almost every component in a database system is affected
                 in terms of adequacy and performance. We show how to
                 design and optimize areas such as storage, transaction
                 management --- comprising recovery and multi-user
                 synchronization --- as well as query processing for
                 XML.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database; XML",
}

@Article{Amer-Yahia:2002:TPQ,
  author =       "S. Amer-Yahia and S. Cho and L. V. S. Lakshmanan and
                 D. Srivastava",
  title =        "Tree pattern query minimization",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "4",
  pages =        "315--331",
  month =        dec,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0076-7",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:03 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011004/20110315.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011004/20110315.pdf",
  abstract =     "Tree patterns form a natural basis to query
                 tree-structured data such as XML and LDAP. To improve
                 the efficiency of tree pattern matching, it is
                 essential to quickly identify and eliminate redundant
                 nodes in the pattern. In this paper, we study tree
                 pattern minimization both in the absence and in the
                 presence of integrity constraints (ICs) on the
                 underlying tree-structured database. In the absence of
                 ICs, we develop a polynomial-time query minimization
                 algorithm called CIM, whose efficiency stems from two
                 key properties: (i) a node cannot be redundant unless
                 its children are; and (ii) the order of elimination of
                 redundant nodes is immaterial. When ICs are considered
                 for minimization, we develop a technique for query
                 minimization based on three fundamental operations:
                 augmentation (an adaptation of the well-known chase
                 procedure), minimization (based on homomorphism
                 techniques), and reduction. We show the surprising
                 result that the algorithm, referred to as ACIM,
                 obtained by first augmenting the tree pattern using
                 ICs, and then applying CIM, always finds the unique
                 minimal equivalent query. While ACIM is polynomial
                 time, it can be expensive in practice because of its
                 inherent non-locality. We then present a fast
                 algorithm, CDM, that identifies and eliminates local
                 redundancies due to ICs, based on propagating
                 ``information labels'' up the tree pattern. CDM can be
                 applied prior to ACIM for improving the minimization
                 efficiency. We complement our analytical results with
                 an experimental study that shows the effectiveness of
                 our tree pattern minimization techniques.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "query minimization; tree patterns; XML",
}

@Article{Chien:2002:ESM,
  author =       "S.-Y. Chien and V. J. Tsotras and C. Zaniolo",
  title =        "Efficient schemes for managing multiversion {XML}
                 documents",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "4",
  pages =        "332--353",
  month =        dec,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0079-4",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:03 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011004/20110332.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011004/20110332.pdf",
  abstract =     "Multiversion support for XML documents is needed in
                 many critical applications, such as software
                 configuration control, cooperative authoring, web
                 information warehouses, and ``e-permanence'' of web
                 documents. In this paper, we introduce efficient and
                 robust techniques for: (i) storing and retrieving; (ii)
                 viewing and exchanging; and (iii) querying multiversion
                 XML documents. We first discuss the limitations of
                 traditional version control methods, such as RCS and
                 SCCS, and then propose novel techniques that overcome
                 their limitations. Initially, we focus on the problem
                 of managing secondary storage efficiently, and
                 introduce an {\em edit-based\/} versioning scheme that
                 enhances RCS with an effective clustering policy based
                 on the concept of page-usefulness. The new scheme
                 drastically improves version retrieval at the expense
                 of a small (linear) space overhead. However, the
                 edit-based approach falls short of achieving objectives
                 (ii) and (iii). Therefore, we introduce and investigate
                 a second scheme, which is reference-based and preserves
                 the structure of the original document. In the
                 reference-based approach, a multiversion document can
                 be represented as yet another XML document, which can
                 be easily exchanged and viewed on the web; furthermore,
                 simple queries are also expressed and supported well
                 under this representation. To achieve objective (i), we
                 extend the page-usefulness clustering technique to the
                 reference-based scheme. After characterizing the
                 asymptotic behavior of the new techniques proposed, the
                 paper presents the results of an experimental study
                 evaluating and comparing their performance.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "historical queries; temporal clustering; temporal
                 indexing; version management; XML database",
}

@Article{Chan:2002:EFX,
  author =       "C.-Y. Chan and P. Felber and M. Garofalakis and R.
                 Rastogi",
  title =        "Efficient filtering of {XML} documents with {XPath}
                 expressions",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "4",
  pages =        "354--379",
  month =        dec,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0077-6",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:03 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011004/20110354.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011004/20110354.pdf",
  abstract =     "The publish/subscribe paradigm is a popular model for
                 allowing publishers (i.e., data generators) to
                 selectively disseminate data to a large number of
                 widely dispersed subscribers (i.e., data consumers) who
                 have registered their interest in specific information
                 items. Early publish/subscribe systems have typically
                 relied on simple subscription mechanisms, such as
                 keyword or ``bag of words'' matching, or simple
                 comparison predicates on attribute values. The
                 emergence of XML as a standard for information exchange
                 on the Internet has led to an increased interest in
                 using more expressive subscription mechanisms (e.g.,
                 based on XPath expressions) that exploit both the
                 structure and the content of published XML documents.
                 Given the increased complexity of these new
                 data-filtering mechanisms, the problem of effectively
                 identifying the subscription profiles that match an
                 incoming XML document poses a difficult and important
                 research challenge. In this paper, we propose a novel
                 index structure, termed XTrie, that supports the
                 efficient filtering of XML documents based on XPath
                 expressions. Our XTrie index structure offers several
                 novel features that, we believe, make it especially
                 attractive for large-scale publish/subscribe systems.
                 First, XTrie is designed to support effective filtering
                 based on complex XPath expressions (as opposed to
                 simple, single-path specifications). Second, our XTrie
                 structure and algorithms are designed to support both
                 ordered and unordered matching of XML data. Third, by
                 indexing on sequences of elements organized in a trie
                 structure and using a sophisticated matching algorithm,
                 XTrie is able to both reduce the number of unnecessary
                 index probes as well as avoid redundant matchings,
                 thereby providing extremely efficient filtering. Our
                 experimental results over a wide range of XML document
                 and XPath expression workloads demonstrate that our
                 XTrie index structure outperforms earlier approaches by
                 wide margins.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data dissemination; document filtering; index
                 structure; XML; XPath",
}

@Article{Ives:2002:XQE,
  author =       "Zachary G. Ives and A. Y. Halevy and D. S. Weld",
  title =        "An {XML} query engine for network-bound data",
  journal =      j-VLDB-J,
  volume =       "11",
  number =       "4",
  pages =        "380--402",
  month =        dec,
  year =         "2002",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0078-5",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:03 MDT 2008",
  bibsource =    "http://link.springer.de/link/service/journals/00778/tocs/t2011004.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/2011004/20110380.htm;
                 http://link.springer.de/link/service/journals/00778/papers/2011004/20110380.pdf",
  abstract =     "XML has become the lingua franca for data exchange and
                 integration across administrative and enterprise
                 boundaries. Nearly all data providers are adding XML
                 import or export capabilities, and standard XML Schemas
                 and DTDs are being promoted for all types of data
                 sharing. The ubiquity of XML has removed one of the
                 major obstacles to integrating data from widely
                 disparate sources --- namely, the heterogeneity of data
                 formats. However, general-purpose integration of data
                 across the wide are a also requires a query processor
                 that can query data sources on demand, receive streamed
                 XML data from them, and combine and restructure the
                 data into new XML output --- while providing good
                 performance for both batch-oriented and ad hoc,
                 interactive queries. This is the goal of the Tukwila
                 data integration system, the first system that focuses
                 on network-bound, dynamic XML data sources. In contrast
                 to previous approaches, which must read, parse, and
                 often store entire XML objects before querying them,
                 Tukwila can return query results even as the data is
                 streaming into the system. Tukwila is built with a new
                 system architecture that extends adaptive query
                 processing and relational-engine techniques into the
                 XML realm, as facilitated by a pair of operators that
                 incrementally evaluate a query's input path expressions
                 as data is read. In this paper, we describe the Tukwila
                 architecture and its novel aspects, and we
                 experimentally demonstrate that Tukwila provides better
                 overall query performance and faster initial answers
                 than existing systems, and has excellent scalability.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data integration; data streams; query processing; web
                 and databases; XML",
}

@Article{Ozsu:2003:NPA,
  author =       "M. Tamer {\"O}zsu",
  title =        "New partnership with {ACM} and update on the journal",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "1",
  pages =        "1--1",
  month =        may,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0089-x",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:05 MDT 2008",
  bibsource =    "http://link.springer-ny.com/link/service/journals/UNKNOWN/tocs/t3012001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/3012001/30120001.htm;
                 http://link.springer.de/link/service/journals/00778/papers/3012001/30120001.pdf",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Sheth:2003:CRK,
  author =       "A. Sheth and S. Thacker and S. Patel",
  title =        "Complex relationships and knowledge discovery support
                 in the {InfoQuilt} system",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "1",
  pages =        "2--27",
  month =        may,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0071-z",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:05 MDT 2008",
  bibsource =    "http://link.springer-ny.com/link/service/journals/UNKNOWN/tocs/t3012001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/3012001/30120002.htm;
                 http://link.springer.de/link/service/journals/00778/papers/3012001/30120002.pdf",
  abstract =     "Support for semantic content is becoming more common
                 in Web-accessible information systems. We see this
                 support emerging with the use of ontologies and
                 machine-readable, annotated documents. The practice of
                 domain modeling coupled with the extraction of
                 domain-specific, contextually relevant metadata also
                 supports the use of semantics. These advancements
                 enable knowledge discovery approaches that define
                 complex relationships between data that is autonomously
                 collected and managed. The InfoQuilt (One of the
                 incarnations of the InfoQuilt system, as applied to the
                 geographic information as part of the NSF Digital
                 Library II initiative is the ADEPT-UGA system [Ade].
                 This research was funded in part by National Science
                 Foundation grant IIS-9817432.) system supports one such
                 knowledge discovery approach. This paper presents
                 (parts of) the InfoQuilt system with the focus on its
                 use for modeling and utilizing complex semantic
                 inter-domain relationships to enable human-assisted
                 knowledge discovery over Web-accessible heterogeneous
                 data. This includes the specification and execution of
                 Information Scale (IScapes), a semantically rich
                 information request and correlation mechanism.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Verykios:2003:BDM,
  author =       "V. S. Verykios and G. V. Moustakides and M. G.
                 Elfeky",
  title =        "A {Bayesian} decision model for cost optimal record
                 matching",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "1",
  pages =        "28--40",
  month =        may,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0072-y",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:05 MDT 2008",
  bibsource =    "http://link.springer-ny.com/link/service/journals/UNKNOWN/tocs/t3012001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/3012001/30120028.htm;
                 http://link.springer.de/link/service/journals/00778/papers/3012001/30120028.pdf",
  abstract =     "In an error-free system with perfectly clean data, the
                 construction of a global view of the data consists of
                 linking --- in relational terms, joining --- two or
                 more tables on their key fields. Unfortunately, most of
                 the time, these data are neither carefully controlled
                 for quality nor necessarily defined commonly across
                 different data sources. As a result, the creation of
                 such a global data view resorts to approximate joins.
                 In this paper, an optimal solution is proposed for the
                 matching or the linking of database record pairs in the
                 presence of inconsistencies, errors or missing values
                 in the data. Existing models for record matching rely
                 on decision rules that minimize the probability of
                 error, that is the probability that a sample (a
                 measurement vector) is assigned to the wrong class. In
                 practice though, minimizing the probability of error is
                 not the best criterion to design a decision rule
                 because the misclassifications of different samples may
                 have different consequences. In this paper we present a
                 decision model that minimizes the cost of making a
                 decision. In particular: (a) we present a decision
                 rule: (b) we prove that this rule is optimal with
                 respect to the cost of a decision: and (c) we compute
                 the probabilities of the two types of errors (Type I
                 and Type II) that incur when this rule is applied. We
                 also present a closed form decision model for a certain
                 class of record comparison pairs along with an example,
                 and results from comparing the proposed cost-based
                 model to the error-based model, for large record
                 comparison spaces.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "cost optimal statistical model; data cleaning; record
                 linkage",
}

@Article{Cui:2003:LTG,
  author =       "Y. Cui and J. Widom",
  title =        "Lineage tracing for general data warehouse
                 transformations",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "1",
  pages =        "41--58",
  month =        may,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0083-8",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:05 MDT 2008",
  bibsource =    "http://link.springer-ny.com/link/service/journals/UNKNOWN/tocs/t3012001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/3012001/30120041.htm;
                 http://link.springer.de/link/service/journals/00778/papers/3012001/30120041.pdf",
  abstract =     "Data warehousing systems integrate information from
                 operational data sources into a central repository to
                 enable analysis and mining of the integrated
                 information. During the integration process, source
                 data typically undergoes a series of {\em
                 transformations}, which may vary from simple algebraic
                 operations or aggregations to complex ``data
                 cleansing'' procedures. In a warehousing environment,
                 the {\em data lineage\/} problem is that of tracing
                 warehouse data items back to the original source items
                 from which they were derived. We formally define the
                 lineage tracing problem in the presence of general data
                 warehouse transformations, and we present algorithms
                 for lineage tracing in this environment. Our tracing
                 procedures take advantage of known structure or
                 properties of transformations when present, but also
                 work in the absence of such information. Our results
                 can be used as the basis for a lineage tracing tool in
                 a general warehousing setting, and also can guide the
                 design of data warehouses that enable efficient lineage
                 tracing.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data lineage; data warehouse; inverse; lineage
                 tracing; transformation",
}

@Article{Medjahed:2003:BBI,
  author =       "B. Medjahed and B. Benatallah and A. Bouguettaya and
                 A. H. H. Ngu and A. K. Elmagarmid",
  title =        "Business-to-business interactions: issues and enabling
                 technologies",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "1",
  pages =        "59--85",
  month =        may,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0087-z",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:05 MDT 2008",
  bibsource =    "http://link.springer-ny.com/link/service/journals/UNKNOWN/tocs/t3012001.htm;
                 http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://link.springer.de/link/service/journals/00778/bibs/3012001/30120059.htm;
                 http://link.springer.de/link/service/journals/00778/papers/3012001/30120059.pdf",
  abstract =     "Business-to-Business (B2B) technologies pre-date the
                 Web. They have existed for at least as long as the
                 Internet. B2B applications were among the first to take
                 advantage of advances in computer networking. The
                 Electronic Data Interchange (EDI) business standard is
                 an illustration of such an early adoption of the
                 advances in computer networking. The ubiquity and the
                 affordability of the Web has made it possible for the
                 masses of businesses to automate their B2B
                 interactions. However, several issues related to scale,
                 content exchange, autonomy, heterogeneity, and other
                 issues still need to be addressed. In this paper, we
                 survey the main techniques, systems, products, and
                 standards for B2B interactions. We propose a set of
                 criteria for assessing the different B2B interaction
                 techniques, standards, and products.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "B2B interactions; components; e-commerce; EDI; Web
                 services; workflows; XML",
}

@Article{Bernstein:2003:GE,
  author =       "Philip A. Bernstein and Yannis Ioannidis and Raghu
                 Ramakrishnan",
  title =        "Guest editorial",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "2",
  pages =        "87--88",
  month =        aug,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0092-2",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:06 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Ramamurthy:2003:CFM,
  author =       "Ravishankar Ramamurthy and David J. DeWitt and Qi
                 Su",
  title =        "A case for fractured mirrors",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "2",
  pages =        "89--101",
  month =        aug,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0093-1",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:06 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The decomposition storage model (DSM) vertically
                 partitions all attributes of a table and has excellent
                 I/O behavior when the number of attributes accessed by
                 a query is small. It also has a better cache footprint
                 than the standard storage model (NSM) used by most
                 database systems. However, DSM incurs a high cost in
                 reconstructing the original tuple from its partitions.
                 We first revisit some of the performance problems
                 associated with DSM and suggest a simple indexing
                 strategy and compare different reconstruction
                 algorithms. Then we propose a new mirroring scheme,
                 termed fractured mirrors, using both NSM and DSM
                 models. This scheme combines the best aspects of both
                 models, along with the added benefit of mirroring to
                 better serve an ad hoc query workload. A prototype
                 system has been built using the Shore storage manager,
                 and performance is evaluated using queries from the
                 TPC-H workload.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data placement; disk mirroring; vertical
                 partitioning",
}

@Article{Chan:2003:RTE,
  author =       "Chee-Yong Chan and Minos Garofalakis and Rajeev
                 Rastogi",
  title =        "{RE}-tree: an efficient index structure for regular
                 expressions",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "2",
  pages =        "102--119",
  month =        aug,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0094-0",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:06 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Due to their expressive power, regular expressions
                 (REs) are quickly becoming an integral part of language
                 specifications for several important application
                 scenarios. Many of these applications have to manage
                 huge databases of RE specifications and need to provide
                 an effective matching mechanism that, given an input
                 string, quickly identifies the REs in the database that
                 match it. In this paper, we propose the RE-tree, a
                 novel index structure for large databases of RE
                 specifications. Given an input query string, the
                 RE-tree speeds up the retrieval of matching REs by
                 focusing the search and comparing the input string with
                 only a small fraction of REs in the database. Even
                 though the RE-tree is similar in spirit to other
                 tree-based structures that have been proposed for
                 indexing multidimensional data, RE indexing is
                 significantly more challenging since REs typically
                 represent infinite sets of strings with no well-defined
                 notion of spatial locality. To address these new
                 challenges, our RE-tree index structure relies on novel
                 measures for comparing the relative sizes of infinite
                 regular languages. We also propose innovative solutions
                 for the various RE-tree operations including the
                 effective splitting of RE-tree nodes and computing a
                 `tight' bounding RE for a collection of REs. Finally,
                 we demonstrate how sampling-based approximation
                 algorithms can be used to significantly speed up the
                 performance of RE-tree operations. Preliminary
                 experimental results with moderately large synthetic
                 data sets indicate that the RE-tree is effective in
                 pruning the search space and easily outperforms naive
                 sequential search approaches.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "index structure; regular expressions; sampling-based
                 approximations; size measures",
}

@Article{Abadi:2003:ANM,
  author =       "Daniel J. Abadi and Don Carney and Ugur
                 {\c{C}}etintemel and Mitch Cherniack and Christian
                 Convey and Sangdon Lee and Michael Stonebraker and
                 Nesime Tatbul and Stan Zdonik",
  title =        "{Aurora}: a new model and architecture for data stream
                 management",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "2",
  pages =        "120--139",
  month =        aug,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0095-z",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:06 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "This paper describes the basic processing model and
                 architecture of Aurora, a new system to manage data
                 streams for monitoring applications. Monitoring
                 applications differ substantially from conventional
                 business data processing. The fact that a software
                 system must process and react to continual inputs from
                 many sources (e.g., sensors) rather than from human
                 operators requires one to rethink the fundamental
                 architecture of a DBMS for this application area. In
                 this paper, we present Aurora, a new DBMS currently
                 under construction at Brandeis University, Brown
                 University, and M.I.T. We first provide an overview of
                 the basic Aurora model and architecture and then
                 describe in detail a stream-oriented set of
                 operators.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "continuous queries; data stream management; database
                 triggers; quality-of-service; real-time systems",
}

@Article{Chandrasekaran:2003:PSS,
  author =       "Sirish Chandrasekaran and Michael J. Franklin",
  title =        "{PSoup}: a system for streaming queries over streaming
                 data",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "2",
  pages =        "140--156",
  month =        aug,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0096-y",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:06 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Recent work on querying data streams has focused on
                 systems where newly arriving data is processed and
                 continuously streamed to the user in real time. In many
                 emerging applications, however, ad hoc queries and/or
                 intermittent connectivity also require the processing
                 of data that arrives prior to query submission or
                 during a period of disconnection. For such
                 applications, we have developed PSoup, a system that
                 combines the processing of ad hoc and continuous
                 queries by treating data and queries symmetrically,
                 allowing new queries to be applied to old data and new
                 data to be applied to old queries. PSoup also supports
                 intermittent connectivity by separating the computation
                 of query results from the delivery of those results.
                 PSoup builds on adaptive query-processing techniques
                 developed in the Telegraph project at UC Berkeley. In
                 this paper, we describe PSoup and present experiments
                 that demonstrate the effectiveness of our approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "disconnected operation; query-data duality; stream
                 query processing",
}

@Article{Agrawal:2003:WRD,
  author =       "Rakesh Agrawal and Peter J. Haas and Jerry Kiernan",
  title =        "Watermarking relational data: framework, algorithms
                 and analysis",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "2",
  pages =        "157--169",
  month =        aug,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0097-x",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:06 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "We enunciate the need for watermarking database
                 relations to deter data piracy, identify the
                 characteristics of relational data that pose unique
                 challenges for watermarking, and delineate desirable
                 properties of a watermarking system for relational
                 data. We then present an effective watermarking
                 technique geared for relational data. This technique
                 ensures that some bit positions of some of the
                 attributes of some of the tuples contain specific
                 values. The specific bit locations and values are
                 algorithmically determined under the control of a
                 secret key known only to the owner of the data. This
                 bit pattern constitutes the watermark. Only if one has
                 access to the secret key can the watermark be detected
                 with high probability. Detecting the watermark requires
                 access neither to the original data nor the watermark,
                 and the watermark can be easily and efficiently
                 maintained in the presence of insertions, updates, and
                 deletions. Our analysis shows that the proposed
                 technique is robust against various forms of malicious
                 attacks as well as benign updates to the data. Using an
                 implementation running on DB2, we also show that the
                 algorithms perform well enough to be used in real-world
                 applications.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "database; information hiding; steganography;
                 watermarking",
}

@Article{Chakrabarti:2003:FAT,
  author =       "Soumen Chakrabarti and Shourya Roy and Mahesh V.
                 Soundalgekar",
  title =        "Fast and accurate text classification via multiple
                 linear discriminant projections",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "2",
  pages =        "170--185",
  month =        aug,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0098-9",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:06 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Support vector machines (SVMs) have shown superb
                 performance for text classification tasks. They are
                 accurate, robust, and quick to apply to test instances.
                 Their only potential drawback is their training time
                 and memory requirement. For $n$ training instances held
                 in memory, the best-known SVM implementations take time
                 proportional to $n^a$, where $a$ is typically between
                 1.8 and 2.1. SVMs have been trained on data sets with
                 several thousand instances, but Web directories today
                 contain millions of instances that are valuable for
                 mapping billions of Web pages into Yahoo!-like
                 directories. We present SIMPL, a nearly linear-time
                 classification algorithm that mimics the strengths of
                 SVMs while avoiding the training bottleneck. It uses
                 Fisher's linear discriminant, a classical tool from
                 statistical pattern recognition, to project training
                 instances to a carefully selected low-dimensional
                 subspace before inducing a decision tree on the
                 projected instances. SIMPL uses efficient sequential
                 scans and sorts and is comparable in speed and memory
                 scalability to widely used naive Bayes (NB)
                 classifiers, but it beats NB accuracy decisively. It
                 not only approaches and sometimes exceeds SVM accuracy,
                 but also beats the running time of a popular SVM
                 implementation by orders of magnitude. While describing
                 SIMPL, we make a detailed experimental comparison of
                 SVM-generated discriminants with Fisher's
                 discriminants, and we also report on an analysis of the
                 cache performance of a popular SVM implementation. Our
                 analysis shows that SIMPL has the potential to be the
                 method of choice for practitioners who want the
                 accuracy of SVMs and the simplicity and speed of naive
                 Bayes classifiers.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "discriminative learning; linear discriminants; text
                 classification",
}

@Article{Fung:2003:CDV,
  author =       "Chi-Wai Fung and Kamalakar Karlapalem and Qing Li",
  title =        "Cost-driven vertical class partitioning for methods in
                 object oriented databases",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "3",
  pages =        "187--210",
  month =        oct,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0084-7",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:07 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In object-oriented databases (OODBs), a method
                 encapsulated in a class typically accesses a few, but
                 not all the instance variables defined in the class. It
                 may thus be preferable to vertically partition the
                 class for reducing irrelevant data (instance variables)
                 accessed by the methods. Our prior work has shown that
                 vertical class partitioning can result in a substantial
                 decrease in the total number of disk accesses incurred
                 for executing a set of applications, but coming up with
                 an optimal vertical class partitioning scheme is a hard
                 problem. In this paper, we present two algorithms for
                 deriving optimal and near-optimal vertical class
                 partitioning schemes. The cost-driven algorithm
                 provides the optimal vertical class partitioning
                 schemes by enumerating, exhaustively, all the schemes
                 and calculating the number of disk accesses required to
                 execute a given set of applications. For this, a cost
                 model for executing a set of methods in an OODB system
                 is developed. Since exhaustive enumeration is costly
                 and only works for classes with a small number of
                 instance variables, a hill-climbing heuristic algorithm
                 (HCHA) is developed, which takes the solution provided
                 by the affinity-based algorithm and improves it,
                 thereby further reducing the total number of disk
                 accesses incurred. We show that the HCHA algorithm
                 provides a reasonable near-optimal vertical class
                 partitioning scheme for executing a given set of
                 applications.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "affinity-based; analytical cost model; cost-driven;
                 hill-climbing heuristic algorithm; method-induced;
                 object-oriented databases; vertical class
                 partitioning",
}

@Article{Li:2003:CCA,
  author =       "Chen Li",
  title =        "Computing complete answers to queries in the presence
                 of limited access patterns",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "3",
  pages =        "211--227",
  month =        oct,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-002-0085-6",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:07 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In data applications such as information integration,
                 there can be limited access patterns to relations,
                 i.e., binding patterns require values to be specified
                 for certain attributes in order to retrieve data from a
                 relation. As a consequence, we cannot retrieve all
                 tuples from these relations. In this article we study
                 the problem of computing the {\em complete\/} answer to
                 a query, i.e., the answer that could be computed if all
                 the tuples could be retrieved. A query is {\em
                 stable\/} if for any instance of the relations in the
                 query, its complete answer can be computed using the
                 access patterns permitted by the relations. We study
                 the problem of testing stability of various classes of
                 queries, including conjunctive queries, unions of
                 conjunctive queries, and conjunctive queries with
                 arithmetic comparisons. We give algorithms and
                 complexity results for these classes of queries. We
                 show that stability of datalog programs is undecidable,
                 and give a sufficient condition for stability of
                 datalog queries. Finally, we study data-dependent
                 computability of the complete answer to a nonstable
                 query, and propose a decision tree for guiding the
                 process to compute the complete answer.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "complete answers to queries; limited access patterns
                 to relations; query stability",
}

@Article{Chua:2003:IBA,
  author =       "Cecil Eng H. Chua and Roger H. L. Chiang and Ee-Peng
                 Lim",
  title =        "Instance-based attribute identification in database
                 integration",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "3",
  pages =        "228--243",
  month =        oct,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0088-y",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:07 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Most research on attribute identification in database
                 integration has focused on integrating attributes using
                 schema and summary information derived from the
                 attribute values. No research has attempted to fully
                 explore the use of attribute values to perform
                 attribute identification. We propose an attribute
                 identification method that employs schema and summary
                 instance information as well as properties of
                 attributes derived from their instances. Unlike other
                 attribute identification methods that match only single
                 attributes, our method matches attribute groups for
                 integration. Because our attribute identification
                 method fully explores data instances, it can identify
                 corresponding attributes to be integrated even when
                 schema information is misleading. Three experiments
                 were performed to validate our attribute identification
                 method. In the first experiment, the heuristic rules
                 derived for attribute classification were evaluated on
                 119 attributes from nine public domain data sets. The
                 second was a controlled experiment validating the
                 robustness of the proposed attribute identification
                 method by introducing erroneous data. The third
                 experiment evaluated the proposed attribute
                 identification method on five data sets extracted from
                 online music stores. The results demonstrated the
                 viability of the proposed method.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "attribute identification; database integration;
                 measures of association",
}

@Article{Helmer:2003:PSF,
  author =       "Sven Helmer and Guido Moerkotte",
  title =        "A performance study of four index structures for
                 set-valued attributes of low cardinality",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "3",
  pages =        "244--261",
  month =        oct,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0106-0",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:07 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The efficient retrieval of data items on set-valued
                 attributes is an important research topic that has
                 attracted little attention so far. We studied and
                 modified four index structures (sequential signature
                 files, signature trees, extendible signature hashing,
                 and inverted files) for a fast retrieval of sets with
                 low cardinality. We compared the index structures by
                 implementing them and subjecting them to extensive
                 experiments, investigating the influence of query set
                 size, database size, domain size, and data distribution
                 (synthetic and real). The results of the experiments
                 clearly indicate that inverted files exhibit the best
                 overall behavior of all tested index structures.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access methods; database management systems; index
                 structures; physical design; set-valued attributes",
}

@Article{Yang:2003:ICM,
  author =       "Jun Yang and Jennifer Widom",
  title =        "Incremental computation and maintenance of temporal
                 aggregates",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "3",
  pages =        "262--283",
  month =        oct,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0107-z",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:07 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "We consider the problems of computing aggregation
                 queries in temporal databases and of maintaining
                 materialized temporal aggregate views efficiently. The
                 latter problem is particularly challenging since a
                 single data update can cause aggregate results to
                 change over the entire time line. We introduce a new
                 index structure called the {\em SB-tree}, which
                 incorporates features from both {\em segment-trees\/}
                 and {\em B-trees}. SB-trees support fast lookup of
                 aggregate results based on time and can be maintained
                 efficiently when the data change. We extend the basic
                 SB-tree index to handle {\em cumulative\/} (also called
                 {\em moving-window\/}) aggregates, considering
                 separatelycases when the window size is or is not fixed
                 in advance. For materialized aggregate views in a
                 temporal database or warehouse, we propose building and
                 maintaining SB-tree indices instead of the views
                 themselves.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access methods; aggregation; B-tree; segment tree;
                 temporal database; view maintenance",
}

@Article{Atluri:2003:GE,
  author =       "Vijay Atluri and Anupam Joshi and Yelena Yesha",
  title =        "Guest editorial",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "4",
  pages =        "285--285",
  month =        nov,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0109-x",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Maedche:2003:MMD,
  author =       "A. Maedche and B. Motik and L. Stojanovic",
  title =        "Managing multiple and distributed ontologies on the
                 {Semantic Web}",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "4",
  pages =        "286--302",
  month =        nov,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0102-4",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In traditional software systems, significant attention
                 is devoted to keeping modules well separated and
                 coherent with respect to functionality, thus ensuring
                 that changes in the system are localized to a handful
                 of modules. Reuse is seen as the key method in reaching
                 that goal. Ontology-based systems on the Semantic Web
                 are just a special class of software systems, so the
                 same principles apply. In this article, we present an
                 integrated framework for managing multiple and
                 distributed ontologies on the Semantic Web. It is based
                 on the representation model for ontologies, trading off
                 between expressivity and tractability. In our
                 framework, we provide features for reusing existing
                 ontologies and for evolving them while retaining the
                 consistency. The approach is implemented within KAON,
                 the Karlsruhe Ontology and Semantic Web tool suite.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "multiple and distributed ontologies; ontology
                 evolution",
}

@Article{Doan:2003:LMO,
  author =       "AnHai Doan and Jayant Madhavan and Robin Dhamankar and
                 Pedro Domingos and Alon Halevy",
  title =        "Learning to match ontologies on the {Semantic Web}",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "4",
  pages =        "303--319",
  month =        nov,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0104-2",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "On the Semantic Web, data will inevitably come from
                 many different ontologies, and information processing
                 across ontologies is not possible without knowing the
                 semantic mappings between them. Manually finding such
                 mappings is tedious, error-prone, and clearly not
                 possible on the Web scale. Hence the development of
                 tools to assist in the ontology mapping process is
                 crucial to the success of the Semantic Web. We describe
                 {\em GLUE}, a system that employs machine learning
                 techniques to find such mappings. Given two ontologies,
                 for each concept in one ontology {\em GLUE\/} finds the
                 most similar concept in the other ontology. We give
                 well-founded probabilistic definitions to several
                 practical similarity measures and show that {\em
                 GLUE\/} can work with all of them. Another key feature
                 of {\em GLUE\/} is that it uses multiple learning
                 strategies, each of which exploits well a different
                 type of information either in the data instances or in
                 the taxonomic structure of the ontologies. To further
                 improve matching accuracy, we extend {\em GLUE\/} to
                 incorporate common-sense knowledge and domain
                 constraints into the matching process. Our approach is
                 thus distinguished in that it works with a variety of
                 well-defined similarity notions and that it efficiently
                 incorporates multiple types of knowledge. We describe a
                 set of experiments on several real-world domains and
                 show that {\em GLUE\/} proposes highly accurate
                 semantic mappings. Finally, we extend {\em GLUE\/} to
                 find complex mappings between ontologies and describe
                 experiments that show the promise of the approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "machine learning; ontology matching; relaxation
                 labeling; Semantic Web",
}

@Article{Halkidi:2003:TOW,
  author =       "Maria Halkidi and Benjamin Nguyen and Iraklis Varlamis
                 and Michalis Vazirgiannis",
  title =        "{THESUS}: Organizing {Web} document collections based
                 on link semantics",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "4",
  pages =        "320--332",
  month =        nov,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0100-6",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The requirements for effective search and management
                 of the WWW are stronger than ever. Currently Web
                 documents are classified based on their content not
                 taking into account the fact that these documents are
                 connected to each other by links. We claim that a
                 page's classification is enriched by the detection of
                 its incoming links' semantics. This would enable
                 effective browsing and enhance the validity of search
                 results in the WWW context. Another aspect that is
                 underaddressed and strictly related to the tasks of
                 browsing and searching is the similarity of documents
                 at the semantic level. The above observations lead us
                 to the adoption of a hierarchy of concepts (ontology)
                 and a thesaurus to exploit links and provide a better
                 characterization of Web documents. The enhancement of
                 document characterization makes operations such as
                 clustering and labeling very interesting. To this end,
                 we devised a system called THESUS. The system deals
                 with an initial sets of Web documents, extracts
                 keywords from all pages' incoming links, and converts
                 them to semantics by mapping them to a domain's
                 ontology. Then a clustering algorithm is applied to
                 discover groups of Web documents. The effectiveness of
                 the clustering process is based on the use of a novel
                 similarity measure between documents characterized by
                 sets of terms. Web documents are organized into
                 thematic subsets based on their semantics. The subsets
                 are then labeled, thereby enabling easier management
                 (browsing, searching, querying) of the Web. In this
                 article, we detail the process of this system and give
                 an experimental analysis of its results.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "document clustering; link analysis; link management;
                 semantics; similarity measure; World Wide Web",
}

@Article{Medjahed:2003:CWS,
  author =       "Brahim Medjahed and Athman Bouguettaya and Ahmed K.
                 Elmagarmid",
  title =        "Composing {Web} services on the {Semantic Web}",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "4",
  pages =        "333--351",
  month =        nov,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0101-5",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Service composition is gaining momentum as the
                 potential {\em silver bullet\/} for the envisioned {\em
                 Semantic Web}. It purports to take the Web to
                 unexplored efficiencies and provide a flexible approach
                 for promoting all types of activities in tomorrow's
                 Web. Applications expected to heavily take advantage of
                 Web service composition include B2B E-commerce and
                 E-government. To date, enabling composite services has
                 largely been an ad hoc, time-consuming, and error-prone
                 process involving repetitive low-level programming. In
                 this paper, we propose an {\em ontology\/}-based
                 framework for the automatic composition of Web
                 services. We present a technique to generate composite
                 services from high-level declarative descriptions. We
                 define formal safeguards for meaningful composition
                 through the use of {\em composability\/} rules. These
                 rules compare the {\em syntactic\/} and {\em
                 semantic\/} features of Web services to determine
                 whether two services are composable. We provide an
                 implementation using an E-government application
                 offering customized services to indigent citizens.
                 Finally, we present an exhaustive performance
                 experiment to assess the scalability of our approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "ontology; Semantic Web; service composition; Web
                 services",
}

@Article{Fileto:2003:POW,
  author =       "Renato Fileto and Ling Liu and Calton Pu and Eduardo
                 Delgado Assad and Claudia Bauzer Medeiros",
  title =        "{POESIA}: {An} ontological workflow approach for
                 composing {Web} services in agriculture",
  journal =      j-VLDB-J,
  volume =       "12",
  number =       "4",
  pages =        "352--367",
  month =        nov,
  year =         "2003",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0103-3",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:08 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "This paper describes the POESIA approach to systematic
                 composition of Web services. This pragmatic approach is
                 strongly centered in the use of domain-specific
                 multidimensional ontologies. Inspired by applications
                 needs and founded on ontologies, workflows, and
                 activity models, POESIA provides well-defined
                 operations (aggregation, specialization, and
                 instantiation) to support the composition of Web
                 services. POESIA complements current proposals for Web
                 services definition and composition by providing a
                 higher degree of abstraction with verifiable
                 consistency properties. We illustrate the POESIA
                 approach using a concrete application scenario in
                 agroenvironmental planning.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "composition of Web services; data integration;
                 ontologies; Semantic Web; semantics of data and
                 processes",
}

@Article{Jensen:2004:MDM,
  author =       "Christian S. Jensen and Augustas Kligys and Torben
                 Bach Pedersen and Igor Timko",
  title =        "Multidimensional data modeling for location-based
                 services",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "1",
  pages =        "1--21",
  month =        jan,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0091-3",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:09 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "With the recent and continuing advances in areas such
                 as wireless communications and positioning
                 technologies, mobile, location-based services are
                 becoming possible. Such services deliver
                 location-dependent content to their users. More
                 specifically, these services may capture the movements
                 and requests of their users in multidimensional
                 databases, i.e., data warehouses, and content delivery
                 may be based on the results of complex queries on these
                 data warehouses. Such queries aggregate detailed data
                 in order to find useful patterns, e.g., in the
                 interaction of a particular user with the services. The
                 application of multidimensional technology in this
                 context poses a range of new challenges. The specific
                 challenge addressed here concerns the provision of an
                 appropriate multidimensional data model. In particular,
                 the paper extends an existing multidimensional data
                 model and algebraic query language to accommodate
                 spatial values that exhibit partial containment
                 relationships instead of the total containment
                 relationships normally assumed in multidimensional data
                 models. Partial containment introduces imprecision in
                 aggregation paths. The paper proposes a method for
                 evaluating the imprecision of such paths. The paper
                 also offers transformations of dimension hierarchies
                 with partial containment relationships to simple
                 hierarchies, to which existing precomputation
                 techniques are applicable.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data modeling; location-based services;
                 multidimensional data; partial containment",
}

@Article{Zhang:2004:PMV,
  author =       "Xin Zhang and Lingli Ding and Elke A. Rundensteiner",
  title =        "Parallel multisource view maintenance",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "1",
  pages =        "22--48",
  month =        jan,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0086-0",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:09 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In a distributed environment, materialized views are
                 used to integrate data from different information
                 sources and then store them in some centralized
                 location. In order to maintain such materialized views,
                 maintenance queries need to be sent to information
                 sources by the data warehouse management system. Due to
                 the independence of the information sources and the
                 data warehouse, concurrency issues are raised between
                 the maintenance queries and the local update
                 transactions at each information source. Recent
                 solutions such as ECA and Strobe tackle such concurrent
                 maintenance, however with the requirement of quiescence
                 of the information sources. SWEEP and POSSE overcome
                 this limitation by decomposing the global maintenance
                 query into smaller subqueries to be sent to every
                 information source and then performing conflict
                 correction locally at the data warehouse. Note that all
                 these previous approaches handle the data updates {\em
                 one at a time}. Hence either some of the information
                 sources or the data warehouse is likely to be idle
                 during most of the maintenance process. In this paper,
                 we propose that a set of updates should be maintained
                 in parallel by several concurrent maintenance processes
                 so that both the information sources as well as the
                 warehouse would be utilized more fully throughout the
                 maintenance process. This parallelism should then
                 improve the overall maintenance performance. For this
                 we have developed a parallel view maintenance
                 algorithm, called PVM, that substantially improves upon
                 the performance of previous maintenance approaches by
                 handling a set of data updates at the same time. The
                 parallel handling of a set of updates is orthogonal to
                 the particular maintenance algorithm applied to the
                 handling of each individual update. In order to perform
                 parallel view maintenance, we have identified two
                 critical issues that must be overcome: (1) detecting
                 maintenance-concurrent data updates in a parallel mode
                 and (2) correcting the problem that the data warehouse
                 commit order may not correspond to the data warehouse
                 update processing order due to parallel maintenance
                 handling. In this work, we provide solutions to both
                 issues. For the former, we insert a middle-layer
                 timestamp assignment module for detecting
                 maintenance-concurrent data updates without requiring
                 any global clock synchronization. For the latter, we
                 introduce the negative counter concept to solve the
                 problem of variant orders of committing effects of data
                 updates to the data warehouse. We provide a proof of
                 the correctness of PVM that guarantees that our
                 strategy indeed generates the correct final data
                 warehouse state. We have implemented both SWEEP and PVM
                 in our EVE data warehousing system. Our performance
                 study demonstrates that a manyfold performance
                 improvement is achieved by PVM over SWEEP.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrent data updates; data warehousing; parallel
                 view maintenance; performance evaluation",
}

@Article{Hristidis:2004:AAA,
  author =       "Vagelis Hristidis and Yannis Papakonstantinou",
  title =        "Algorithms and applications for answering ranked
                 queries using ranked views",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "1",
  pages =        "49--70",
  month =        jan,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0099-8",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:09 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Ranked queries return the top objects of a database
                 according to a preference function. We present and
                 evaluate (experimentally and theoretically) a core
                 algorithm that answers ranked queries in an efficient
                 pipelined manner using materialized ranked views. We
                 use and extend the core algorithm in the described
                 PREFER and MERGE systems. PREFER precomputes a set of
                 materialized views that provide guaranteed query
                 performance. We present an algorithm that selects a
                 near optimal set of views under space constraints. We
                 also describe multiple optimizations and implementation
                 aspects of the downloadable version of PREFER. Then we
                 discuss MERGE, which operates at a metabroker and
                 answers ranked queries by retrieving a minimal number
                 of objects from sources that offer ranked queries. A
                 speculative version of the pipelining algorithm is
                 described.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "materialization; merge ranked views; ranked queries",
}

@Article{Khan:2004:REO,
  author =       "Latifur Khan and Dennis McLeod and Eduard Hovy",
  title =        "Retrieval effectiveness of an ontology-based model for
                 information selection",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "1",
  pages =        "71--85",
  month =        jan,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0105-1",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:09 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Technology in the field of digital media generates
                 huge amounts of nontextual information, audio, video,
                 and images, along with more familiar textual
                 information. The potential for exchange and retrieval
                 of information is vast and daunting. The key problem in
                 achieving efficient and user-friendly retrieval is the
                 development of a search mechanism to guarantee delivery
                 of minimal irrelevant information (high precision)
                 while insuring relevant information is not overlooked
                 (high recall). The traditional solution employs
                 keyword-based search. The only documents retrieved are
                 those containing user-specified keywords. But many
                 documents convey desired semantic information without
                 containing these keywords. This limitation is
                 frequently addressed through query expansion mechanisms
                 based on the statistical co-occurrence of terms. Recall
                 is increased, but at the expense of deteriorating
                 precision. One can overcome this problem by indexing
                 documents according to context and meaning rather than
                 keywords, although this requires a method of converting
                 words to meanings and the creation of a meaning-based
                 index structure. We have solved the problem of an index
                 structure through the design and implementation of a
                 concept-based model using domain-dependent ontologies.
                 An ontology is a collection of concepts and their
                 interrelationships that provide an abstract view of an
                 application domain. With regard to converting words to
                 meaning, the key issue is to identify appropriate
                 concepts that both describe and identify documents as
                 well as language employed in user requests. This paper
                 describes an automatic mechanism for selecting these
                 concepts. An important novelty is a scalable
                 disambiguation algorithm that prunes irrelevant
                 concepts and allows relevant ones to associate with
                 documents and participate in query generation. We also
                 propose an automatic query expansion mechanism that
                 deals with user requests expressed in natural language.
                 This mechanism generates database queries with
                 appropriate and relevant expansion through knowledge
                 encoded in ontology form. Focusing on audio data, we
                 have constructed a demonstration prototype. We have
                 experimentally and analytically shown that our model,
                 compared to keyword search, achieves a significantly
                 higher degree of precision and recall. The techniques
                 employed can be applied to the problem of information
                 selection in all media types.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "audio; metadata; ontology; precision; recall; SQL",
}

@Article{Donderler:2004:RBS,
  author =       "Mehmet Emin D{\"o}nderler and {\"O}zg{\"u}r Ulusoy and
                 Ugur G{\"u}d{\"u}kbay",
  title =        "Rule-based spatiotemporal query processing for video
                 databases",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "1",
  pages =        "86--103",
  month =        jan,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0114-0",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:09 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In our earlier work, we proposed an architecture for a
                 Web-based video database management system (VDBMS)
                 providing an integrated support for spatiotemporal and
                 semantic queries. In this paper, we focus on the task
                 of spatiotemporal query processing and also propose an
                 SQL-like video query language that has the capability
                 to handle a broad range of spatiotemporal queries. The
                 language is rule-based in that it allows users to
                 express spatial conditions in terms of Prolog-type
                 predicates. Spatiotemporal query processing is carried
                 out in three main stages: query recognition, query
                 decomposition, and query execution.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "content-based retrieval; inference rules; multimedia
                 databases; spatiotemporal query processing; video
                 databases",
}

@Article{Yu:2004:QHD,
  author =       "Cui Yu and St{\'e}phane Bressan and Beng Chin Ooi and
                 Kian-Lee Tan",
  title =        "Querying high-dimensional data in single-dimensional
                 space",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "2",
  pages =        "105--119",
  month =        may,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0121-9",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:10 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In this paper, we propose a new tunable index scheme,
                 called iMinMax($\theta$), that maps points in
                 high-dimensional spaces to single-dimensional values
                 determined by their maximum or minimum values among all
                 dimensions. By varying the tuning ``knob'', $\theta$,
                 we can obtain different families of iMinMax structures
                 that are optimized for different distributions of data
                 sets. The transformed data can then be indexed using
                 existing single-dimensional indexing structures such as
                 the B$^+$-trees. Queries in the high-dimensional space
                 have to be transformed into queries in the
                 single-dimensional space and evaluated there. We
                 present efficient algorithms for evaluating window
                 queries as range queries on the single-dimensional
                 space. We conducted an extensive performance study to
                 evaluate the effectiveness of the proposed schemes. Our
                 results show that iMinMax($\theta$) outperforms
                 existing techniques, including the Pyramid scheme and
                 VA-file, by a wide margin. We then describe how iMinMax
                 could be used in approximate K-nearest neighbor (KNN)
                 search, and we present a comparative study against the
                 recently proposed iDistance, a specialized KNN indexing
                 method.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "edge; high-dimensional data; iMinMax($\theta$);
                 single-dimensional space; window and KNN queries",
}

@Article{Dori:2004:VVS,
  author =       "Dov Dori",
  title =        "{ViSWeb} --- the {Visual Semantic Web}: unifying human
                 and machine knowledge representations with
                 {Object-Process Methodology}",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "2",
  pages =        "120--147",
  month =        may,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0120-x",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:10 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The Visual Semantic Web (ViSWeb) is a new paradigm for
                 enhancing the current Semantic Web technology. Based on
                 Object-Process Methodology (OPM), which enables
                 modeling of systems in a single graphic and textual
                 model, ViSWeb provides for representation of knowledge
                 over the Web in a unified way that caters to human
                 perceptions while also being machine processable. The
                 advantages of the ViSWeb approach include equivalent
                 graphic-text knowledge representation, visual
                 navigability, semantic sentence interpretation,
                 specification of system dynamics, and complexity
                 management. Arguing against the claim that humans and
                 machines need to look at different knowledge
                 representation formats, the principles and basics of
                 various graphic and textual knowledge representations
                 are presented and examined as candidates for ViSWeb
                 foundation. Since OPM is shown to be most adequate for
                 the task, ViSWeb is developed as an OPM-based layer on
                 top of XML/RDF/OWL to express knowledge visually and in
                 natural language. Both the graphic and the textual
                 representations are strictly equivalent. Being
                 intuitive yet formal, they are not only understandable
                 to humans but are also amenable to computer processing.
                 The ability to use such bimodal knowledge
                 representation is potentially a major step forward in
                 the evolution of the Semantic Web.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "conceptual graphs; knowledge representation;
                 object-process methodology; Semantic Web; Visual
                 Semantic Web",
}

@Article{Fu:2004:EHA,
  author =       "Lixin Fu and Sanguthevar Rajasekaran",
  title =        "Evaluating holistic aggregators efficiently for very
                 large datasets",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "2",
  pages =        "148--161",
  month =        may,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0112-2",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:10 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In data warehousing applications, numerous OLAP
                 queries involve the processing of holistic aggregators
                 such as computing the ``top $n$,'' median, quantiles,
                 etc. In this paper, we present a novel approach called
                 dynamic bucketing to efficiently evaluate these
                 aggregators. We partition data into equiwidth buckets
                 and further partition dense buckets into subbuckets as
                 needed by allocating and reclaiming memory space. The
                 bucketing process dynamically adapts to the input order
                 and distribution of input datasets. The histograms of
                 the buckets and subbuckets are stored in our new data
                 structure called structure trees. A recent selection
                 algorithm based on regular sampling is generalized and
                 its analysis extended. We have also compared our new
                 algorithms with this generalized algorithm and several
                 other recent algorithms. Experimental results show that
                 our new algorithms significantly outperform prior ones
                 not only in the runtime but also in accuracy.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "aggregation; dynamic bucketing; quantiles",
}

@Article{Rahal:2004:ETU,
  author =       "Amira Rahal and Qiang Zhu and Per-{\AA}ke Larson",
  title =        "Evolutionary techniques for updating query cost models
                 in a dynamic multidatabase environment",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "2",
  pages =        "162--176",
  month =        may,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0110-4",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:10 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Deriving local cost models for query optimization in a
                 dynamic multidatabase system (MDBS) is a challenging
                 issue. In this paper, we study how to evolve a query
                 cost model to capture a slowly-changing dynamic MDBS
                 environment so that the cost model is kept up-to-date
                 all the time. Two novel evolutionary techniques, i.e.,
                 the shifting method and the block-moving method, are
                 proposed. The former updates a cost model by taking
                 up-to-date information from a new sample query into
                 consideration at each step, while the latter considers
                 a block (batch) of new sample queries at each step. The
                 relevant issues, including derivation of recurrence
                 updating formulas, development of efficient algorithms,
                 analysis and comparison of complexities, and design of
                 an integrated scheme to apply the two methods
                 adaptively, are studied. Our theoretical and
                 experimental results demonstrate that the proposed
                 techniques are quite promising in maintaining accurate
                 cost models efficiently for a slowly changing dynamic
                 MDBS environment. Besides the application to MDBSs, the
                 proposed techniques can also be applied to the
                 automatic maintenance of cost models in self-managing
                 database systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "cost model; evolutionary technique; multidatabase;
                 query optimization; self-managing database",
}

@Article{Adi:2004:ASM,
  author =       "Asaf Adi and Opher Etzion",
  title =        "{Amit} --- the situation manager",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "2",
  pages =        "177--203",
  month =        may,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-003-0108-y",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:10 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "This paper presents the ``situation manager'', a tool
                 that includes both a language and an efficient runtime
                 execution mechanism aimed at reducing the complexity of
                 active applications. This tool follows the observation
                 that in many cases there is a gap between current tools
                 that enable one to react to a single event (following
                 the ECA: event-condition-action paradigm) and the
                 reality in which a single event may not require any
                 reaction; however, the reaction should be given to
                 patterns over the event history. The concept of
                 presented in this paper extends the concept of in its
                 expressive power, flexibility, and usability. This
                 paper motivates the work, surveys other efforts in this
                 area, and discusses both the language and the execution
                 model.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "active databases; active technology; composite events;
                 high-level languages",
}

@Article{Freytag:2004:BPV,
  author =       "Johann-Christoph Freytag and Serge Abiteboul and Mike
                 Carey",
  title =        "Best papers of {VLDB} 2003",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "3",
  pages =        "205--206",
  month =        sep,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0129-1",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:11 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Ilyas:2004:STJ,
  author =       "Ihab F. Ilyas and Walid G. Aref and Ahmed K.
                 Elmagarmid",
  title =        "Supporting top-$k$ join queries in relational
                 databases",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "3",
  pages =        "207--221",
  month =        sep,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0128-2",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:11 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Ranking queries, also known as top-$k$ queries,
                 produce results that are ordered on some computed
                 score. Typically, these queries involve joins, where
                 users are usually interested only in the top-$k$ join
                 results. Top-$k$ queries are dominant in many emerging
                 applications, e.g., multimedia retrieval by content,
                 Web databases, data mining, middlewares, and most
                 information retrieval applications. Current relational
                 query processors do not handle ranking queries
                 efficiently, especially when joins are involved. In
                 this paper, we address supporting top-$k$ join queries
                 in relational query processors. We introduce a new
                 rank-join algorithm that makes use of the individual
                 orders of its inputs to produce join results ordered on
                 a user-specified scoring function. The idea is to rank
                 the join results progressively during the join
                 operation. We introduce two physical query operators
                 based on variants of ripple join that implement the
                 rank-join algorithm. The operators are nonblocking and
                 can be integrated into pipelined execution plans. We
                 also propose an efficient heuristic designed to
                 optimize a top-$k$ join query by choosing the best join
                 order. We address several practical issues and
                 optimization heuristics to integrate the new join
                 operators in practical query processors. We implement
                 the new operators inside a prototype database engine
                 based on PREDATOR. The experimental evaluation of our
                 approach compares recent algorithms for joining ranked
                 inputs and shows superior performance.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "query operators; rank aggregarion; ranking; top-$k$
                 queries",
}

@Article{Papadimitriou:2004:AUS,
  author =       "Spiros Papadimitriou and Anthony Brockwell and
                 Christos Faloutsos",
  title =        "Adaptive, unsupervised stream mining",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "3",
  pages =        "222--239",
  month =        sep,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0130-8",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:11 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Sensor devices and embedded processors are becoming
                 widespread, especially in measurement/monitoring
                 applications. Their limited resources (CPU, memory
                 and/or communication bandwidth, and power) pose some
                 interesting challenges. We need concise, expressive
                 models to represent the important features of the data
                 and that lend themselves to efficient estimation. In
                 particular, under these severe constraints, we want
                 models and estimation methods that (a) require little
                 memory and a single pass over the data, (b) can adapt
                 and handle arbitrary periodic components, and (c) can
                 deal with various types of noise. We propose
                 ${\mathrm{AWSOM}}$ (Arbitrary Window Stream mOdeling
                 Method), which allows sensors in remote or hostile
                 environments to efficiently and effectively discover
                 interesting patterns and trends. This can be done
                 automatically, i.e., with no prior inspection of the
                 data or any user intervention and expert tuning before
                 or during data gathering. Our algorithms require
                 limited resources and can thus be incorporated into
                 sensors --- possibly alongside a distributed query
                 processing engine [10,6,27]. Updates are performed in
                 constant time with respect to stream size using
                 logarithmic space. Existing forecasting methods
                 (SARIMA, GARCH, etc.) and ``traditional'' Fourier and
                 wavelet analysis fall short on one or more of these
                 requirements. To the best of our knowledge,
                 ${\mathrm{AWSOM}}$ is the first framework that combines
                 all of the above characteristics. Experiments on real
                 and synthetic datasets demonstrate that
                 ${\mathrm{AWSOM}}$ discovers meaningful patterns over
                 long time periods. Thus, the patterns can also be used
                 to make long-range forecasts, which are notoriously
                 difficult to perform. In fact, ${\mathrm{AWSOM}}$
                 outperforms manually set up autoregressive models, both
                 in terms of long-term pattern detection and modeling
                 and by at least $10 \times$ in resource consumption.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Labrinidis:2004:ETB,
  author =       "Alexandros Labrinidis and Nick Roussopoulos",
  title =        "Exploring the tradeoff between performance and data
                 freshness in database-driven {Web} servers",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "3",
  pages =        "240--255",
  month =        sep,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0131-7",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:11 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Personalization, advertising, and the sheer volume of
                 online data generate a staggering amount of dynamic Web
                 content. In addition to Web caching, view
                 materialization has been shown to accelerate the
                 generation of dynamic Web content. View materialization
                 is an attractive solution as it decouples the serving
                 of access requests from the handling of updates. In the
                 context of the Web, selecting which views to
                 materialize must be decided online and needs to
                 consider both performance and data freshness, which we
                 refer to as the online view selection problem. In this
                 paper, we define data freshness metrics, provide an
                 adaptive algorithm for the online view selection
                 problem that is based on user-specified data freshness
                 requirements, and present experimental results.
                 Furthermore, we examine alternative metrics for data
                 freshness and extend our proposed algorithm to handle
                 multiple users and alternative definitions of data
                 freshness.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{He:2004:AIW,
  author =       "Hai He and Weiyi Meng and Clement Yu and Zonghuan
                 Wu",
  title =        "Automatic integration of {Web} search interfaces with
                 {WISE}-Integrator",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "3",
  pages =        "256--273",
  month =        sep,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0126-4",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:11 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "An increasing number of databases are becoming Web
                 accessible through form-based search interfaces, and
                 many of these sources are database-driven e-commerce
                 sites. It is a daunting task for users to access
                 numerous Web sites individually to get the desired
                 information. Hence, providing a unified access to
                 multiple e-commerce search engines selling similar
                 products is of great importance in allowing users to
                 search and compare products from multiple sites with
                 ease. One key task for providing such a capability is
                 to integrate the Web search interfaces of these
                 e-commerce search engines so that user queries can be
                 submitted against the integrated interface. Currently,
                 integrating such search interfaces is carried out
                 either manually or semiautomatically, which is
                 inefficient and difficult to maintain. In this paper,
                 we present WISE-Integrator --- a tool that performs
                 automatic integration of Web Interfaces of Search
                 Engines. WISE-Integrator explores a rich set of special
                 metainformation that exists in Web search interfaces
                 and uses the information to identify matching
                 attributes from different search interfaces for
                 integration. It also resolves domain differences of
                 matching attributes. In this paper, we also discuss how
                 to automatically extract information from search
                 interfaces that is needed by WISE-Integrator to perform
                 automatic interface integration. Our experimental
                 results, based on 143 real-world search interfaces in
                 four different domains, indicate that WISE-Integrator
                 can achieve high attribute matching accuracy and can
                 produce high-quality integrated search interfaces
                 without human interactions.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "attribute matching; interface extraction; metasearch;
                 schema integration; Web search interface integration",
}

@Article{Velegrakis:2004:PMC,
  author =       "Yannis Velegrakis and Ren{\'e} J. Miller and Lucian
                 Popa",
  title =        "Preserving mapping consistency under schema changes",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "3",
  pages =        "274--293",
  month =        sep,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0136-2",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:11 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In dynamic environments like the Web, data sources may
                 change not only their data but also their schemas,
                 their semantics, and their query capabilities. When a
                 mapping is left inconsistent by a schema change, it has
                 to be detected and updated. We present a novel
                 framework and a tool (ToMAS) for automatically adapting
                 (rewriting) mappings as schemas evolve. Our approach
                 considers not only local changes to a schema but also
                 changes that may affect and transform many components
                 of a schema. Our algorithm detects mappings affected by
                 structural or constraint changes and generates all the
                 rewritings that are consistent with the semantics of
                 the changed schemas. Our approach explicitly models
                 mapping choices made by a user and maintains these
                 choices, whenever possible, as the schemas and mappings
                 evolve. When there is more than one candidate
                 rewriting, the algorithm may rank them based on how
                 close they are to the semantics of the existing
                 mappings.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Florescu:2004:BSX,
  author =       "Daniela Florescu and Chris Hillery and Donald Kossmann
                 and Paul Lucas and Fabio Riccardi and Till Westmann and
                 J. Carey and Arvind Sundararajan",
  title =        "The {BEA} streaming {XQuery} processor",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "3",
  pages =        "294--315",
  month =        sep,
  year =         "2004",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-004-0137-1",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:11 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "This paper describes the design, implementation, and
                 performance characteristics of a commercial XQuery
                 processing engine, the BEA streaming XQuery processor.
                 This XQuery engine was designed to provide high
                 performance for message-processing applications, i.e.,
                 for transforming XML data streams. The engine is a
                 central component of the 8.1 release of BEA's
                 WebLogic Integration (WLI) product. The BEA XQuery
                 engine is fully compliant with the August 2002 draft of
                 the W3C XML Query Language specification and we are
                 currently porting it to the latest version of the
                 XQuery language (July 2004). A goal of this paper is to
                 describe how a fully compliant yet efficient XQuery
                 engine has been built from a few relatively simple
                 components and well-understood technologies.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Gehrke:2004:GES,
  author =       "Johannes Gehrke and M. Hellerstein",
  title =        "{Guest Editorial} to the special issue on data stream
                 processing",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "4",
  pages =        "317--317",
  month =        dec,
  year =         "2004",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:12 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Yang:2004:FHQ,
  author =       "Huai Yang and Li Lee and Wynne Hsu",
  title =        "Finding hot query patterns over an {XQuery} stream",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "4",
  pages =        "318--332",
  month =        dec,
  year =         "2004",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:12 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Caching query results is one efficient approach to
                 improving the performance of XML management systems.
                 This entails the discovery of frequent XML queries
                 issued by users. In this paper, we model user queries
                 as a stream of XML query pattern trees and mine the
                 frequent query patterns over the query stream. To
                 facilitate the one-pass mining process, we devise a
                 novel data structure called DTS to summarize the
                 pattern trees seen so far. By grouping the incoming
                 pattern trees into batches, we can dynamically mark the
                 active portion of the current batch in DTS and limit
                 the enumeration of candidate trees to only the
                 currently active pattern trees. We also design another
                 summary data structure called ECTree that provides for
                 the incremental computation of the frequent tree
                 patterns over the query stream. Based on the above two
                 constructs, we present two mining algorithms called
                 XQSMinerI and XQSMinerII. XQSMinerI is fast, but it
                 tends to overestimate, while XQSMinerII adopts a
                 filter-and-refine approach to minimize the amount of
                 overestimation. Experimental results show that the
                 proposed methods are both efficient and scalable and
                 require only small memory footprints.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "frequent pattern mining; pattern tree; stream mining;
                 tree mining; XML query pattern",
}

@Article{Babcock:2004:OSD,
  author =       "Brian Babcock and Shivnath Babu and Mayur Datar and
                 Rajeev Motwani and Dilys Thomas",
  title =        "Operator scheduling in data stream systems",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "4",
  pages =        "333--353",
  month =        dec,
  year =         "2004",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:12 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In many applications involving continuous data
                 streams, data arrival is bursty and data rate
                 fluctuates over time. Systems that seek to give rapid
                 or real-time query responses in such an environment
                 must be prepared to deal gracefully with bursts in data
                 arrival without compromising system performance. We
                 discuss one strategy for processing bursty streams ---
                 adaptive, load-aware scheduling of query operators to
                 minimize resource consumption during times of peak
                 load. We show that the choice of an operator scheduling
                 strategy can have significant impact on the runtime
                 system memory usage as well as output latency. Our aim
                 is to design a scheduling strategy that minimizes the
                 maximum runtime system memory while maintaining the
                 output latency within prespecified bounds. We first
                 present Chain scheduling, an operator scheduling
                 strategy for data stream systems that is near-optimal
                 in minimizing runtime memory usage for any collection
                 of single-stream queries involving selections,
                 projections, and foreign-key joins with stored
                 relations. Chain scheduling also performs well for
                 queries with sliding-window joins over multiple streams
                 and multiple queries of the above types. However,
                 during bursts in input streams, when there is a buildup
                 of unprocessed tuples, Chain scheduling may lead to
                 high output latency. We study the online problem of
                 minimizing maximum runtime memory, subject to a
                 constraint on maximum latency. We present preliminary
                 observations, negative results, and heuristics for this
                 problem. A thorough experimental evaluation is provided
                 where we demonstrate the potential benefits of Chain
                 scheduling and its different variants, compare it with
                 competing scheduling strategies, and validate our
                 analytical conclusions.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data streams; latency; memory management; scheduling",
}

@Article{Ganguly:2004:TSE,
  author =       "Sumit Ganguly and Minos Garofalakis and Rajeev
                 Rastogi",
  title =        "Tracking set-expression cardinalities over continuous
                 update streams",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "4",
  pages =        "354--369",
  month =        dec,
  year =         "2004",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:12 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "There is growing interest in algorithms for processing
                 and querying continuous data streams (i.e., data seen
                 only once in a fixed order) with limited memory
                 resources. In its most general form, a data stream is
                 actually an update stream, i.e., comprising data-item
                 deletions as well as insertions. Such massive update
                 streams arise naturally in several application domains
                 (e.g., monitoring of large IP network installations or
                 processing of retail-chain transactions). Estimating
                 the cardinality of set expressions defined over several
                 (possibly distributed) update streams is perhaps one of
                 the most fundamental query classes of interest; as an
                 example, such a query may ask ``what is the number of
                 distinct IP source addresses seen in passing packets
                 from both router $R_1$ and $R_2$ but not router
                 $R_3$?''. Earlier work only addressed very restricted
                 forms of this problem, focusing solely on the special
                 case of insert-only streams and specific operators
                 (e.g., union). In this paper, we propose the first
                 space-efficient algorithmic solution for estimating the
                 cardinality of full-fledged set expressions over
                 general update streams. Our estimation algorithms are
                 probabilistic in nature and rely on a novel, hash-based
                 synopsis data structure, termed ''2-level hash
                 sketch''. We demonstrate how our 2-level hash sketch
                 synopses can be used to provide low-error,
                 high-confidence estimates for the cardinality of set
                 expressions (including operators such as set union,
                 intersection, and difference) over continuous update
                 streams, using only space that is significantly
                 sublinear in the sizes of the streaming input
                 (multi-)sets. Furthermore, our estimators never require
                 rescanning or resampling of past stream items,
                 regardless of the number of deletions in the stream. We
                 also present lower bounds for the problem,
                 demonstrating that the space usage of our estimation
                 algorithms is within small factors of the optimal.
                 Finally, we propose an optimized, time-efficient stream
                 synopsis (based on 2-level hash sketches) that provides
                 similar, strong accuracy-space guarantees while
                 requiring only guaranteed logarithmic maintenance time
                 per update, thus making our methods applicable for
                 truly rapid-rate data streams. Our results from an
                 empirical study of our synopsis and estimation
                 techniques verify the effectiveness of our approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "approximate query processing; data streams; data
                 synopses; randomized algorithms; set expressions",
}

@Article{Balakrishnan:2004:RA,
  author =       "Hari Balakrishnan and Magdalena Balazinska and Don
                 Carney and U{\=g}ur {\c{C}}etintemel and Mitch
                 Cherniack and Christian Convey and Eddie Galvez and Jon
                 Salz and Michael Stonebraker and Nesime Tatbul and
                 Richard Tibbetts and Stan Zdonik",
  title =        "Retrospective on {Aurora}",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "4",
  pages =        "370--383",
  month =        dec,
  year =         "2004",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:12 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "This experience paper summarizes the key lessons we
                 learned throughout the design and implementation of the
                 Aurora stream-processing engine. For the past 2 years,
                 we have built five stream-based applications using
                 Aurora. We first describe in detail these applications
                 and their implementation in Aurora. We then reflect on
                 the design of Aurora based on this experience. Finally,
                 we discuss our initial ideas on a follow-on project,
                 called Borealis, whose goal is to eliminate the
                 limitations of Aurora as well as to address new key
                 challenges and applications in the stream-processing
                 domain.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data stream management; distributed stream processing;
                 monitoring applications; quality-of-service;
                 stream-processing engines",
}

@Article{Sharaf:2004:BEE,
  author =       "A. Sharaf and Jonathan Beaver and Alexandros
                 Labrinidis and K. Chrysanthis",
  title =        "Balancing energy efficiency and quality of aggregate
                 data in sensor networks",
  journal =      j-VLDB-J,
  volume =       "13",
  number =       "4",
  pages =        "384--403",
  month =        dec,
  year =         "2004",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:12 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In-network aggregation has been proposed as one method
                 for reducing energy consumption in sensor networks. In
                 this paper, we explore two ideas related to further
                 reducing energy consumption in the context of
                 in-network aggregation. The first is by influencing the
                 construction of the routing trees for sensor networks
                 with the goal of reducing the size of transmitted data.
                 To this end, we propose a group-aware network
                 configuration method that ``clusters'' along the same
                 path sensor nodes that belong to the same group. The
                 second idea involves imposing a hierarchy of output
                 filters on the sensor network with the goal of both
                 reducing the size of transmitted data and minimizing
                 the number of transmitted messages. More specifically,
                 we propose a framework to use temporal coherency
                 tolerances in conjunction with in-network aggregation
                 to save energy at the sensor nodes while maintaining
                 specified quality of data. These tolerances are based
                 on user preferences or can be dictated by the network
                 in cases where the network cannot support the current
                 tolerance level. Our framework, called TiNA, works on
                 top of existing in-network aggregation schemes. We
                 evaluate experimentally our proposed schemes in the
                 context of existing in-network aggregation schemes. We
                 present experimental results measuring energy
                 consumption, response time, and quality of data for
                 Group-By queries. Overall, our schemes provide
                 significant energy savings with respect to
                 communication and a negligible drop in quality of
                 data.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "in-network query processing; power-aware computing;
                 semantic routing; sensor networks",
}

@Article{Ozsu:2005:E,
  author =       "Tamer {\"O}zsu",
  title =        "Editorial",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "1--1",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Gao:2005:JOT,
  author =       "Dengfeng Gao and S. Jensen and T. Snodgrass and D.
                 Soo",
  title =        "Join operations in temporal databases",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "2--29",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Joins are arguably the most important relational
                 operators. Poor implementations are tantamount to
                 computing the Cartesian product of the input relations.
                 In a temporal database, the problem is more acute for
                 two reasons. First, conventional techniques are
                 designed for the evaluation of joins with equality
                 predicates rather than the inequality predicates
                 prevalent in valid-time queries. Second, the presence
                 of temporally varying data dramatically increases the
                 size of a database. These factors indicate that
                 specialized techniques are needed to efficiently
                 evaluate temporal joins. We address this need for
                 efficient join evaluation in temporal databases. Our
                 purpose is twofold. We first survey all previously
                 proposed temporal join operators. While many temporal
                 join operators have been defined in previous work, this
                 work has been done largely in isolation from competing
                 proposals, with little, if any, comparison of the
                 various operators. We then address evaluation
                 algorithms, comparing the applicability of various
                 algorithms to the temporal join operators and
                 describing a performance study involving algorithms for
                 one important operator, the temporal equijoin. Our
                 focus, with respect to implementation, is on
                 non-index-based join algorithms. Such algorithms do not
                 rely on auxiliary access paths but may exploit sort
                 orderings to achieve efficiency.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "attribute skew; interval join; partition join;
                 sort-merge join; temporal Cartesian product; temporal
                 join; timestamp skew",
}

@Article{Balmin:2005:SQX,
  author =       "Andrey Balmin and Yannis Papakonstantinou",
  title =        "Storing and querying {XML} data using denormalized
                 relational databases",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "30--49",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "XML database systems emerge as a result of the
                 acceptance of the XML data model. Recent works have
                 followed the promising approach of building XML
                 database management systems on underlying
                 RDBMS's. Achieving query processing performance
                 reduces to two questions: (i) How should the XML data
                 be decomposed into data that are stored in the RDBMS?
                 (ii) How should the XML query be translated into an
                 efficient plan that sends one or more SQL queries to
                 the underlying RDBMS and combines the data into the XML
                 result? We provide a formal framework for XML
                 Schema-driven decompositions, which encompasses the
                 decompositions proposed in prior work and extends them
                 with decompositions that employ denormalized tables and
                 binary-coded XML fragments. We provide corresponding
                 query processing algorithms that translate the XML
                 query conditions into conditions on the relational
                 tables and assemble the decomposed data into the XML
                 query result. Our key performance focus is the response
                 time for delivering the first results of a query. The
                 most effective of the described decompositions have
                 been implemented in XCacheDB, an XML DBMS built on top
                 of a commercial RDBMS, which serves as our experimental
                 basis. We present experiments and analysis that point
                 to a class of decompositions, called inlined
                 decompositions, that improve query performance for full
                 results and first results, without significant increase
                 in the size of the database.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Gal:2005:FME,
  author =       "Avigdor Gal and Ateret Anaby-Tavor and Alberto
                 Trombetta and Danilo Montesi",
  title =        "A framework for modeling and evaluating automatic
                 semantic reconciliation",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "50--67",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The introduction of the Semantic Web vision and the
                 shift toward machine understandable Web resources has
                 unearthed the importance of automatic semantic
                 reconciliation. Consequently, new tools for automating
                 the process were proposed. In this work we present a
                 formal model of semantic reconciliation and analyze in
                 a systematic manner the properties of the process
                 outcome, primarily the inherent uncertainty of the
                 matching process and how it reflects on the resulting
                 mappings. An important feature of this research is the
                 identification and analysis of factors that impact the
                 effectiveness of algorithms for automatic semantic
                 reconciliation, leading, it is hoped, to the design of
                 better algorithms by reducing the uncertainty of
                 existing algorithms. Against this background we
                 empirically study the aptitude of two algorithms to
                 correctly match concepts. This research is both timely
                 and practical in light of recent attempts to develop
                 and utilize methods for automatic semantic
                 reconciliation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "mapping; ontology versioning; semantic
                 interoperability",
}

@Article{Halevy:2005:SML,
  author =       "Y. Halevy and G. Ives and Dan Suciu and Igor
                 Tatarinov",
  title =        "Schema mediation for large-scale semantic data
                 sharing",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "68--83",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Intuitively, data management and data integration
                 tools should be well suited for exchanging information
                 in a semantically meaningful way. Unfortunately, they
                 suffer from two significant problems: they typically
                 require a common and comprehensive schema design before
                 they can be used to store or share information, and
                 they are difficult to extend because schema evolution
                 is heavyweight and may break backward compatibility. As
                 a result, many large-scale data sharing tasks are more
                 easily facilitated by non-database-oriented tools that
                 have little support for semantics. The goal of the peer
                 data management system (PDMS) is to address this need:
                 we propose the use of a decentralized, easily
                 extensible data management architecture in which any
                 user can contribute new data, schema information, or
                 even mappings between other peers' schemas.
                 PDMSs represent a natural step beyond data integration
                 systems, replacing their single logical schema with an
                 interlinked collection of semantic mappings between
                 peers' individual schemas. This paper considers
                 the problem of schema mediation in a PDMS. Our first
                 contribution is a flexible language for mediating
                 between peer schemas that extends known data
                 integration formalisms to our more complex
                 architecture. We precisely characterize the complexity
                 of query answering for our language. Next, we describe
                 a reformulation algorithm for our language that
                 generalizes both global-as-view and local-as-view query
                 answering algorithms. Then we describe several methods
                 for optimizing the reformulation algorithm and an
                 initial set of experiments studying its performance.
                 Finally, we define and consider several {\em global\/}
                 problems in managing semantic mappings in a PDMS.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data integration; peer data management; schema
                 mediation; Web and databases",
}

@Article{Benatallah:2005:AWS,
  author =       "Boualem Benatallah and Mohand-Said Hacid and Alain
                 Leger and Christophe Rey and Farouk Toumani",
  title =        "On automating {Web} services discovery",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "84--96",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "One of the challenging problems that Web service
                 technology faces is the ability to effectively discover
                 services based on their capabilities. We present an
                 approach to tackling this problem in the context of
                 description logics (DLs). We formalize service
                 discovery as a new instance of the problem of rewriting
                 concepts using terminologies. We call this new instance
                 the {\em best covering problem}. We provide a
                 formalization of the {\em best covering problem\/} in
                 the framework of DL-based ontologies and propose a
                 hypergraph-based algorithm to effectively compute best
                 covers of a given request. We propose a novel
                 matchmaking algorithm that takes as input a service
                 request (or query) $Q$ and an ontology $\mathcal{T}$ of
                 services and finds a set of services called a ``best
                 cover'' of $Q$ whose descriptions contain as much {\em
                 common information\/} with $Q$ as possible and as
                 little {\em extra information\/} with respect to $Q$ as
                 possible. We have implemented the proposed discovery
                 technique and used the developed prototype in the
                 context of the {\em Multilingual Knowledge Based
                 European Electronic Marketplace\/} (MKBEEM) project.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "description logics; discovery; hypergraphs; semantic
                 matchmaking; Web services",
}

@Article{Sattler:2005:CBQ,
  author =       "Kai-Uwe Sattler and Ingolf Geist and Eike Schallehn",
  title =        "Concept-based querying in mediator systems",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "97--111",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "One approach to overcoming heterogeneity as a part of
                 data integration in mediator systems is the use of
                 metadata in the form of a vocabulary or ontology to
                 represent domain knowledge explicitly. This requires
                 including this meta level during query formulation and
                 processing. In this paper, we address this problem in
                 the context of a mediator that uses a concept-based
                 integration model and an extension of the XQuery
                 language called CQuery. This mediator has been
                 developed as part of a project for integrating data
                 about cultural assets. We describe the language
                 extensions and their semantics as well as the rewriting
                 and evaluation steps. Furthermore, we discuss aspects
                 of caching and keyword-based search in support of an
                 efficient query formulation and processing.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data integration; mediator systems; query processing",
}

@Article{Tzitzikas:2005:MTB,
  author =       "Yannis Tzitzikas and Nicolas Spyratos and Panos
                 Constantopoulos",
  title =        "Mediators over taxonomy-based information sources",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "1",
  pages =        "112--136",
  month =        mar,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:14 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "We propose a mediator model for providing integrated
                 and unified access to multiple taxonomy-based sources.
                 Each source comprises a taxonomy and a database that
                 indexes objects under the terms of the taxonomy. A
                 mediator comprises a taxonomy and a set of relations
                 between the mediator's and the sources'
                 terms, called articulations. By combining different
                 modes of query evaluation at the sources and the
                 mediator and different types of query translation, a
                 flexible, efficient scheme of mediator operation is
                 obtained that can accommodate various application needs
                 and levels of answer quality. We adopt a simple
                 conceptual modeling approach (taxonomies and
                 intertaxonomy mappings) and we illustrate its
                 advantages in terms of ease of use, uniformity,
                 scalability, and efficiency. These characteristics make
                 this proposal appropriate for a large-scale network of
                 sources and mediators.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "approximate query translation; information
                 integration; mediators; taxonomies",
}

@Article{Gunopulos:2005:SEM,
  author =       "Dimitrios Gunopulos and George Kollios and J. Tsotras
                 and Carlotta Domeniconi",
  title =        "Selectivity estimators for multidimensional range
                 queries over real attributes",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "137--154",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Estimating the selectivity of multidimensional range
                 queries over real valued attributes has significant
                 applications in data exploration and database query
                 optimization. In this paper, we consider the following
                 problem: given a table of $d$ attributes whose domain
                 is the real numbers and a query that specifies a range
                 in each dimension, find a good approximation of the
                 number of records in the table that satisfy the query.
                 The simplest approach to tackle this problem is to
                 assume that the attributes are independent. More
                 accurate estimators try to capture the joint data
                 distribution of the attributes. In databases, such
                 estimators include the construction of multidimensional
                 histograms, random sampling, or the wavelet transform.
                 In statistics, kernel estimation techniques are being
                 used. Many traditional approaches assume that attribute
                 values come from discrete, finite domains, where
                 different values have high frequencies. However, for
                 many novel applications (as in temporal, spatial, and
                 multimedia databases) attribute values come from the
                 infinite domain of real numbers. Consequently, each
                 value appears very infrequently, a characteristic that
                 affects the behavior and effectiveness of the
                 estimator. Moreover, real-life data exhibit attribute
                 correlations that also affect the estimator. We present
                 a new histogram technique that is designed to
                 approximate the density of multidimensional datasets
                 with real attributes. Our technique defines buckets of
                 variable size and allows the buckets to overlap. The
                 size of the cells is based on the local density of the
                 data. The use of overlapping buckets allows a more
                 compact approximation of the data distribution. We also
                 show how to generalize kernel density estimators and
                 how to apply them to the multidimensional query
                 approximation problem. Finally, we compare the accuracy
                 of the proposed techniques with existing techniques
                 using real and synthetic datasets. The experimental
                 results show that the proposed techniques behave more
                 accurately in high dimensionalities than previous
                 approaches.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Alhajj:2005:VFC,
  author =       "Reda Alhajj and Faruk Polat and Cem Y{\'\i}lmaz",
  title =        "Views as first-class citizens in object-oriented
                 databases",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "155--169",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Extensibility and dynamic schema evolution are among
                 the attractive features that lead to the wide
                 acceptance of the object-oriented paradigm. Not knowing
                 all class hierarchy details should not prevent a user
                 from introducing new classes when necessary. Naive or
                 professional users may define new classes either by
                 using class definition constructs or as views. However,
                 improper placement of such classes leads to a flat
                 hierarchy with many things duplicated. To overcome this
                 problem, we automated the process in order to help the
                 user find the most appropriate position with respect to
                 her class in the hierarchy regardless of her knowledge
                 of the hierarchy. The system must be responsible for
                 the proper placement of new classes because only the
                 system has complete knowledge of the details of the
                 class hierarchy, especially in a dynamic environment
                 where changes are very frequent. In other published
                 work, we proved that to define a view it is enough to
                 have the set of objects that qualify to be in a view in
                 addition to having message expressions (possible paths)
                 that lead to desired values within those objects. Here,
                 we go further to map a view that is intended to be
                 persistent into a class. Then we investigate the proper
                 position of that class in the hierarchy. To achieve
                 this, we consider current characteristics of a new
                 class in order to derive its relationship with other
                 existing classes in the hierarchy. Another advantage of
                 the presented model is that views that generate new
                 objects are still updatable simply because we based the
                 creation of new objects on existing identities. In
                 other words, an object participates inside view objects
                 by its identity regardless of which particular values
                 from that object are of interest to the view. Values
                 are reachable via message expressions, not violating
                 encapsulation. This way, actual values are present in
                 only one place and can be updated.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "class hierarchy; object-oriented databases;
                 reusability; schema evolution; views",
}

@Article{Zhang:2005:OSM,
  author =       "Donghui Zhang and J. Tsotras",
  title =        "Optimizing spatial {Min\slash Max} aggregations",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "170--181",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Aggregate computation over a collection of spatial
                 objects appears in many real-life applications.
                 Aggregates are computed on values (weights) associated
                 with spatial objects, for example, the temperature or
                 rainfall over the area covered by the object. In this
                 paper we concentrate on MIN/MAX aggregations: ``given a
                 query rectangle, find the minimum/maximum weight among
                 all objects intersecting the query rectangle.''
                 Traditionally such queries have been performed as range
                 searches. Assuming that objects are indexed by a
                 spatial access method (SAM), the MIN/MAX is computed
                 while retrieving those objects intersecting the query
                 interval. This requires effort proportional to the
                 number of objects satisfying the query, which may be
                 large. A better approach is to maintain aggregate
                 information among the index nodes of the spatial access
                 method; then various index paths can be eliminated
                 during the range search. Yet another approach is to
                 build a specialized index that maintains the aggregate
                 incrementally. We propose four novel optimizations for
                 improving the performance of MIN/MAX queries when an
                 index structure (traditional or specialized) is
                 present. Moreover, we introduce the MR-tree, an
                 R-tree-like dynamic specialized index that incorporates
                 all four optimizations. Our experiments show that the
                 MR-tree offers drastic performance improvement over
                 previous solutions. As a byproduct of this work we
                 present an optimized version of the MSB-tree, an index
                 that has been proposed for the MIN/MAX computation over
                 1D interval objects.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "indexing; MIN/MAX; spatial aggregates",
}

@Article{Perich:2005:CJP,
  author =       "Filip Perich and Anupam Joshi and Yelena Yesha and Tim
                 Finin",
  title =        "Collaborative joins in a pervasive computing
                 environment",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "182--196",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "We present a collaborative query processing protocol
                 based on the principles of Contract Nets. The protocol
                 is designed for pervasive computing environments where,
                 in addition to operating on limited computing and
                 battery resources, mobile devices cannot always rely on
                 being able to access the wired infrastructure. Devices,
                 therefore, need to collaborate with each other in order
                 to obtain data otherwise inaccessible due to the nature
                 of the environment. Furthermore, by intelligently using
                 answers cached by peers, devices can reduce their
                 computation cost. We show the effectiveness of our
                 approach by evaluating performance of devices querying
                 for data while moving in a citylike environment.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "distributed join processing; mobile ad hoc networks;
                 peer-to-peer computing; pervasive computing
                 environments; query processing",
}

@Article{Josifovski:2005:QXS,
  author =       "Vanja Josifovski and Marcus Fontoura and Attila
                 Barta",
  title =        "Querying {XML} streams",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "197--210",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Efficient querying of XML streams will be one of the
                 fundamental features of next-generation information
                 systems. In this paper we propose the TurboXPath path
                 processor, which accepts a language equivalent to a
                 subset of the for-let-where constructs of XQuery over a
                 single document. TurboXPath can be extended to provide
                 full XQuery support or used to augment federated
                 database engines for efficient handling of queries over
                 XML data streams produced by external sources.
                 Internally, TurboXPath uses a tree-shaped path
                 expression with multiple outputs to drive the
                 execution. The result of a query execution is a
                 sequence of tuples of XML fragments matching the output
                 nodes. Based on a streamed execution model, TurboXPath
                 scales up to large documents and has limited memory
                 consumption for increased concurrency. Experimental
                 evaluation of a prototype demonstrates performance
                 gains compared to other state-of-the-art path
                 processors.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

@Article{Aggarwal:2005:EEA,
  author =       "C. Aggarwal and S. Yu",
  title =        "An effective and efficient algorithm for
                 high-dimensional outlier detection",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "211--221",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The outlier detection problem has important
                 applications in the field of fraud detection, network
                 robustness analysis, and intrusion detection. Most such
                 applications are most important for high-dimensional
                 domains in which the data can contain hundreds of
                 dimensions. Many recent algorithms have been proposed
                 for outlier detection that use several concepts of
                 proximity in order to find the outliers based on their
                 relationship to the other points in the data. However,
                 in high-dimensional space, the data are sparse and
                 concepts using the notion of proximity fail to retain
                 their effectiveness. In fact, the sparsity of
                 high-dimensional data can be understood in a different
                 way so as to imply that every point is an equally good
                 outlier from the perspective of distance-based
                 definitions. Consequently, for high-dimensional data,
                 the notion of finding meaningful outliers becomes
                 substantially more complex and nonobvious. In this
                 paper, we discuss new techniques for outlier detection
                 that find the outliers by studying the behavior of
                 projections from the data set.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data mining; high-dimensional spaces; outlier
                 detection",
}

@Article{Yao:2005:HBL,
  author =       "D. Yao and Cyrus Shahabi and Per-{\AA}ke Larson",
  title =        "Hash-based labeling techniques for storage scaling",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "222--237",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Scalable storage architectures allow for the addition
                 or removal of storage devices to increase storage
                 capacity and bandwidth or retire older devices.
                 Assuming random placement of data objects across
                 multiple storage devices of a storage pool, our
                 optimization objective is to redistribute a minimum
                 number of objects after scaling the pool. In addition,
                 a uniform distribution, and hence a balanced load,
                 should be ensured after redistribution. Moreover, the
                 redistributed objects should be retrieved efficiently
                 during the normal mode of operation: in one I/O access
                 and with low complexity computation. To achieve this,
                 we propose an algorithm called random disk labeling
                 (RDL), based on double hashing, where storage can be
                 added or removed without any increase in complexity. We
                 compare RDL with other proposed techniques and
                 demonstrate its effectiveness through
                 experimentation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "load balancing; random data placement; scalable
                 storage systems",
}

@Article{Kollios:2005:IMO,
  author =       "George Kollios and Dimitris Papadopoulos and Dimitrios
                 Gunopulos and J. Tsotras",
  title =        "Indexing mobile objects using dual transformations",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "238--256",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "With the recent advances in wireless networks,
                 embedded systems, and GPS technology, databases that
                 manage the location of moving objects have received
                 increased interest. In this paper, we present indexing
                 techniques for moving object databases. In particular,
                 we propose methods to index moving objects in order to
                 efficiently answer range queries about their current
                 and future positions. This problem appears in real-life
                 applications such as predicting future congestion areas
                 in a highway system or allocating more bandwidth for
                 areas where a high concentration of mobile phones is
                 imminent. We address the problem in external memory and
                 present dynamic solutions, both for the one-dimensional
                 and the two-dimensional cases. Our approach transforms
                 the problem into a dual space that is easier to index.
                 Important in this dynamic environment is not only query
                 performance but also the update processing, given the
                 large number of moving objects that issue updates. We
                 compare the dual-transformation approach with the
                 TPR-tree, an efficient method for indexing moving
                 objects that is based on time-parameterized index
                 nodes. An experimental evaluation shows that the
                 dual-transformation approach provides comparable query
                 performance but has much faster update processing.
                 Moreover, the dual method does not require establishing
                 a predefined query horizon.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "access methods; mobile objects; spatiotemporal
                 databases",
}

@Article{Jaluta:2005:CCR,
  author =       "Ibrahim Jaluta and Seppo Sippu and Eljas
                 Soisalon-Soininen",
  title =        "Concurrency control and recovery for balanced {B}-link
                 trees",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "2",
  pages =        "257--277",
  month =        apr,
  year =         "2005",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:15 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In this paper we present new concurrent and
                 recoverable B-link-tree algorithms. Unlike previous
                 algorithms, ours maintain the balance of the B-link
                 tree at all times, so that a logarithmic time bound for
                 a search or an update operation is guaranteed under
                 arbitrary sequences of record insertions and deletions.
                 A database transaction can contain any number of
                 operations of the form ``fetch the first (or next)
                 matching record'', ``insert a record'', or ``delete a
                 record'', where database records are identified by
                 their primary keys. Repeatable-read-level isolation for
                 transactions is guaranteed by key-range locking. The
                 algorithms apply the write-ahead logging (WAL) protocol
                 and the steal and no-force buffering policies for index
                 and data pages. Record inserts and deletes on leaf
                 pages of a B-link tree are logged using physiological
                 redo-undo log records. Each structure modification such
                 as a page split or merge is made an atomic action by
                 keeping the pages involved in the modification latched
                 for the (short) duration of the modification and the
                 logging of that modification; at most two B-link-tree
                 pages are kept $X$-latched at a time. Each structure
                 modification brings the B-link tree into a structurally
                 consistent and balanced state whenever the tree was
                 structurally consistent and balanced initially. Each
                 structure modification is logged using a single
                 physiological redo-only log record. Thus, a structure
                 modification will never be undone even if the
                 transaction that gave rise to it eventually aborts. In
                 restart recovery, the redo pass of our ARIES-based
                 recovery protocol will always produce a structurally
                 consistent and balanced B-link tree, on which the
                 database updates by backward-rolling transactions can
                 always be undone logically, when a physical
                 (page-oriented) undo is no longer possible.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "concurrency control; recovery; transaction;
                 tree-structure modifications",
}

@Article{Gaasterland:2005:SID,
  author =       "Terry Gaasterland and H. V. Jagadish and Louiqa
                 Raschid",
  title =        "Special issue on data management, analysis, and mining
                 for the life sciences",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "3",
  pages =        "279--280",
  month =        sep,
  year =         "2005",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-005-0165-5",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:16 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://springerlink.metapress.com/openurl.asp?genre=issue&issn=0938-1287&volume=14&issue=3;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0938-1287&volume=14&issue=3&spage=279",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
}

%%% TO DO: [23-Aug-2006] ACM Portal lacks data for v14n4, v15n1, and v15n2

@Article{Tian:2005:PMC,
  author =       "Yuanyuan Tian and Sandeep Tata and Richard A. Hankins
                 and Jignesh M. Patel",
  title =        "Practical methods for constructing suffix trees",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "3",
  pages =        "281--299",
  month =        sep,
  year =         "2005",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-005-0154-8",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:16 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://springerlink.metapress.com/openurl.asp?genre=issue&issn=0938-1287&volume=14&issue=3;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0938-1287&volume=14&issue=3&spage=281",
  abstract =     "Sequence datasets are ubiquitous in modern
                 life-science applications, and querying sequences is a
                 common and critical operation in many of these
                 applications. The suffix tree is a versatile data
                 structure that can be used to evaluate a wide variety
                 of queries on sequence datasets, including evaluating
                 exact and approximate string matches, and finding
                 repeat patterns. However, methods for constructing
                 suffix trees are often very time-consuming, especially
                 for suffix trees that are large and do not fit in the
                 available main memory. Even when the suffix tree fits
                 in memory, it turns out that the processor cache
                 behavior of theoretically optimal suffix tree
                 construction methods is poor, resulting in poor
                 performance. Currently, there are a large number of
                 algorithms for constructing suffix trees, but the
                 practical tradeoffs in using these algorithms for
                 different scenarios are not well characterized. In this
                 paper, we explore suffix tree construction algorithms
                 over a wide spectrum of data sources and sizes. First,
                 we show that on modern processors, a cache-efficient
                 algorithm with $O(n^2)$ worst-case complexity
                 outperforms popular linear time algorithms like Ukkonen
                 and McCreight, even for in-memory construction. For
                 larger datasets, the disk I/O requirement quickly
                 becomes the bottleneck in each algorithm's performance.
                 To address this problem, we describe two approaches.
                 First, we present a buffer management strategy for the
                 $O(n^2)$ algorithm. The resulting new algorithm, which
                 we call ``Top Down Disk-based'' (TDD), scales to sizes
                 much larger than have been previously described in
                 literature. This approach far outperforms the best
                 known disk-based construction methods. Second, we
                 present a new disk-based suffix tree construction
                 algorithm that is based on a sort-merge paradigm, and
                 show that for constructing very large suffix trees with
                 very little resources, this algorithm is more efficient
                 than TDD.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "sequence matching; suffix tree construction",
}

@Article{Claypool:2005:SYD,
  author =       "Kajal T. Claypool and Elke A. Rundensteiner",
  title =        "Sync your data: update propagation for heterogeneous
                 protein databases",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "3",
  pages =        "300--317",
  month =        sep,
  year =         "2005",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-005-0155-7",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:16 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://springerlink.metapress.com/openurl.asp?genre=issue&issn=0938-1287&volume=14&issue=3;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0938-1287&volume=14&issue=3&spage=300",
  abstract =     "The traditional model of bench (wet) chemistry in many
                 life sciences domain is today actively complemented by
                 computer-based discoveries utilizing the growing number
                 of online data sources. A typical {\em computer-based
                 discovery\/} scenario for many life scientists includes
                 the creation of local caches of pertinent information
                 from multiple online resources such as Swissprot
                 [Nucleic Acid Res. 1 (28), 45--48 (2000)], PIR [Nucleic
                 Acids Res. 28 (1), 41--44 (2000)], PDB [The Protein
                 DataBank. Wiley, New York (2003)], to enable efficient
                 data analysis. This local caching of data, however,
                 exposes their research and eventual results to the
                 problems of data staleness, that is, cached data may
                 quickly be obsolete or incorrect, dependent on the
                 updates that are made to the source data. This
                 represents a significant challenge to the scientific
                 community, forcing scientists to be continuously aware
                 of the frequent changes made to public data sources,
                 and more importantly aware of the potential effects on
                 their own derived data sets during the course of their
                 research. To address this significant challenge, in
                 this paper we present an approach for handling update
                 propagation between heterogeneous databases,
                 guaranteeing data freshness for scientists irrespective
                 of their choice of data source and its underlying data
                 model or interface. We propose a {\em middle-layer\/}
                 --based solution wherein first the change in the online
                 data source is translated to a sequence of changes in
                 the middle-layer; next each change in the middle-layer
                 is propagated through an algebraic representation of
                 the translation between the source and the target; and
                 finally the net-change is translated to a set of
                 changes that are then applied to the local cache. In
                 this paper, we present our algebraic model that
                 represents the mapping of the online resource to the
                 local cache, as well as our adaptive propagation
                 algorithm that can incrementally propagate both schema
                 and data changes from the source to the cache in a data
                 model independent manner. We present a case study based
                 on a joint ongoing project with our collaborators in
                 the Chemistry Department at UMass-Lowell to explicate
                 our approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data transformation; data translation; schema
                 evolution; update propagation; view maintenance",
}

@Article{Conery:2005:RBW,
  author =       "John S. Conery and Julian M. Catchen and Michael
                 Lynch",
  title =        "Rule-based workflow management for bioinformatics",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "3",
  pages =        "318--329",
  month =        sep,
  year =         "2005",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-005-0153-9",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:16 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://springerlink.metapress.com/openurl.asp?genre=issue&issn=0938-1287&volume=14&issue=3;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0938-1287&volume=14&issue=3&spage=318",
  abstract =     "We describe a data-centric software architecture for
                 bioinformatics workflows and a rule-based workflow
                 enactment system that uses declarative specifications
                 of data dependences between steps to automatically
                 order the execution of those steps. A data-centric view
                 allows researchers to develop abstract descriptions of
                 workflow products and provides mechanisms for
                 describing workflow steps as objects. The rule-based
                 approach supports an iterative design methodology for
                 creating new workflows, where steps can be developed in
                 small, incremental updates, and the object orientation
                 allows workflow steps developed for one project to be
                 reused in other projects.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "bioinformatics; rule-based system; workflow",
}

@Article{Thakkar:2005:COE,
  author =       "Snehal Thakkar and Jos{\'e} Luis Ambite and Craig A.
                 Knoblock",
  title =        "Composing, optimizing, and executing plans for
                 bioinformatics web services",
  journal =      j-VLDB-J,
  volume =       "14",
  number =       "3",
  pages =        "330--353",
  month =        sep,
  year =         "2005",
  CODEN =        "VLDBFR",
  DOI =          "http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00778-005-0158-4",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:16 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://springerlink.metapress.com/openurl.asp?genre=issue&issn=0938-1287&volume=14&issue=3;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0938-1287&volume=14&issue=3&spage=330",
  abstract =     "The emergence of a large number of bioinformatics
                 datasets on the Internet has resulted in the need for
                 flexible and efficient approaches to integrate
                 information from multiple bioinformatics data sources
                 and services. In this paper, we present our approach to
                 automatically generate composition plans for web
                 services, optimize the composition plans, and execute
                 these plans efficiently. While data integration
                 techniques have been applied to the bioinformatics
                 domain, the focus has been on answering specific user
                 queries. In contrast, we focus on automatically
                 generating {\em parameterized\/} integration plans that
                 can be hosted as web services that respond to a range
                 of inputs. In addition, we present two novel techniques
                 that improve the execution time of the generated plans
                 by reducing the number of requests to the existing data
                 sources and by executing the generated plan more
                 efficiently. The first optimization technique, called
                 tuple-level filtering, analyzes the source/service
                 descriptions in order to automatically insert filtering
                 conditions in the composition plans that result in
                 fewer requests to the component web services. To ensure
                 that the filtering conditions can be evaluated, this
                 technique may include sensing operations in the
                 integration plan. The savings due to filtering
                 significantly exceed the cost of the sensing
                 operations. The second optimization technique consists
                 in mapping the integration plans into programs that can
                 be executed by a dataflow-style, streaming execution
                 engine. We use real-world bioinformatics web services
                 to show experimentally that (1) our automatic
                 composition techniques can efficiently generate
                 parameterized plans that integrate data from large
                 numbers of existing services and (2) our optimization
                 techniques can significantly reduce the response time
                 of the generated integration plans.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "bioinformatics; data integration; dataflow-style
                 streaming execution; query optimization; Web service
                 composition",
}

@Article{Vlachos:2006:IMT,
  author =       "Michail Vlachos and Marios Hadjieleftheriou and
                 Dimitrios Gunopulos and Eamonn Keogh",
  title =        "Indexing {Multidimensional Time-Series}",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "1",
  pages =        "1--20",
  month =        jan,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:17 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "While most time series data mining research has
                 concentrated on providing solutions for a single
                 distance function, in this work we motivate the need
                 for an index structure that can support multiple
                 distance measures. Our specific area of interest is the
                 efficient retrieval and analysis of similar
                 trajectories. Trajectory datasets are very common in
                 environmental applications, mobility experiments, and
                 video surveillance and are especially important for the
                 discovery of certain biological patterns. Our primary
                 similarity measure is based on the longest common
                 subsequence (LCSS) model that offers enhanced
                 robustness, particularly for noisy data, which are
                 encountered very often in real-world applications.
                 However, our index is able to accommodate other
                 distance measures as well, including the ubiquitous
                 Euclidean distance and the increasingly popular dynamic
                 time warping (DTW). While other researchers have
                 advocated one or other of these similarity measures, a
                 major contribution of our work is the ability to
                 support all these measures without the need to
                 restructure the index. Our framework guarantees no
                 false dismissals and can also be tailored to provide
                 much faster response time at the expense of slightly
                 reduced precision/recall. The experimental results
                 demonstrate that our index can help speed up the
                 computation of expensive similarity measures such as
                 the LCSS and the DTW.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "dynamic time warping; ensemble index; longest common
                 subsequence; motion capture; trajectories",
}

@Article{Zheng:2006:GPI,
  author =       "Baihua Zheng and Jianliang Xu and Wang-Chien Lee and
                 Lun Lee",
  title =        "Grid-partition index: a hybrid method for
                 nearest-neighbor queries in wireless location-based
                 services",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "1",
  pages =        "21--39",
  month =        jan,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:17 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Traditional nearest-neighbor (NN) search is based on
                 two basic indexing approaches: object-based indexing
                 and solution-based indexing. The former is constructed
                 based on the locations of data objects: using some
                 distance heuristics on object locations. The latter is
                 built on a precomputed solution space. Thus, NN queries
                 can be reduced to and processed as simple point queries
                 in this solution space. Both approaches exhibit some
                 disadvantages, especially when employed for wireless
                 data broadcast in mobile computing environments. In
                 this paper, we introduce a new index method, called the
                 {\em grid-partition index}, to support NN search in
                 both on-demand access and periodic broadcast modes of
                 mobile computing. The grid-partition index is
                 constructed based on the Voronoi diagram, i.e., the
                 solution space of NN queries. However, it has two
                 distinctive characteristics. First, it divides the
                 solution space into grid cells such that a query point
                 can be efficiently mapped into a grid cell around which
                 the nearest object is located. This significantly
                 reduces the search space. Second, the grid-partition
                 index stores the {\em objects\/} that are potential NNs
                 of any query falling within the cell. The storage of
                 objects, instead of the Voronoi cells, makes the
                 grid-partition index a hybrid of the solution-based and
                 object-based approaches. As a result, it achieves a
                 much more compact representation than the pure
                 solution-based approach and avoids backtracked
                 traversals required in the typical object-based
                 approach, thus realizing the advantages of both
                 approaches. We develop an incremental construction
                 algorithm to address the issue of object update. In
                 addition, we present a cost model to approximate the
                 search cost of different grid partitioning schemes. The
                 performances of the grid-partition index and existing
                 indexes are evaluated using both synthetic and real
                 data. The results show that, overall, the
                 grid-partition index significantly outperforms
                 object-based indexes and solution-based indexes.
                 Furthermore, we extend the grid-partition index to
                 support continuous-nearest-neighbor search. Both
                 algorithms and experimental results are presented.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "continuous-nearest-neighbor search; index structure;
                 location-dependent data; nearest-neighbor search;
                 wireless broadcast",
}

@Article{Tamir:2006:CGM,
  author =       "Raz Tamir and Yehuda Singer",
  title =        "On a confidence gain measure for association rule
                 discovery and scoring",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "1",
  pages =        "40--52",
  month =        jan,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:17 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "This article presents a new interestingness measure
                 for association rules called confidence gain (CG).
                 Focus is given to extraction of human associations
                 rather than associations between market products. There
                 are two main differences between the two (human and
                 market associations). The first difference is the
                 strong asymmetry of human associations (e.g., the
                 association ``shampoo''--``hair'' is much stronger than
                 ``hair''--``shampoo''), where in market products
                 asymmetry is less intuitive and less evident. The
                 second is the background knowledge humans employ when
                 presented with a stimulus (input phrase).CG calculates
                 the local confidence of a given term compared to its
                 average confidence throughout a given database. CG is
                 found to outperform several association measures since
                 it captures both the asymmetric notion of an
                 association (as in the confidence measure) while adding
                 the comparison to an expected confidence (as in the
                 lift measure). The use of average confidence introduces
                 the ``background knowledge'' notion into the CG
                 measure. Various experiments have shown that CG and
                 local confidence gain (a low-complexity version of CG)
                 successfully generate association rules when compared
                 to human free associations. The experiments include a
                 large-scale ``free sssociation Turing test'' where
                 human free associations were compared to associations
                 generated by the CG and other association measures.
                 Rules discovered by CG were found to be significantly
                 better than those discovered by other measures. CG can
                 be used for many purposes, such as personalization,
                 sense disambiguation, query expansion, and improving
                 classification performance of small item sets within
                 large databases. Although CG was found to be useful for
                 Internet data retrieval, results can be easily used
                 over any type of database.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "association generation; association rule validation
                 methods; confidence gain; Web data management; Web
                 mining",
}

@Article{Bremer:2006:IDD,
  author =       "Jan-Marco Bremer and Michael Gertz",
  title =        "Integrating document and data retrieval based on
                 {XML}",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "1",
  pages =        "53--83",
  month =        jan,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:17 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "For querying structured and semistructured data, data
                 retrieval and document retrieval are two valuable and
                 complementary techniques that have not yet been fully
                 integrated. In this paper, we introduce integrated
                 information retrieval (IIR), an XML-based retrieval
                 approach that closes this gap. We introduce the syntax
                 and semantics of an extension of the XQuery language
                 called XQuery/IR. The extended language realizes IIR
                 and thereby allows users to formulate new kinds of
                 queries by nesting ranked document retrieval and
                 precise data retrieval queries. Furthermore, we detail
                 index structures and efficient query processing
                 approaches for implementing XQuery/IR. Based on a new
                 identification scheme for nodes in node-labeled tree
                 structures, the extended index structures require only
                 a fraction of the space of comparable index structures
                 that only support data retrieval.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data retrieval; document retrieval; index structures;
                 integrated information retrievals; structural join;
                 XML",
}

@Article{Ogras:2006:OSD,
  author =       "Y. Ogras and Hakan Ferhatosmanoglu",
  title =        "Online summarization of dynamic time series data",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "1",
  pages =        "84--98",
  month =        jan,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:17 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Managing large-scale time series databases has
                 attracted significant attention in the database
                 community recently. Related fundamental problems such
                 as dimensionality reduction, transformation, pattern
                 mining, and similarity search have been studied
                 extensively. Although the time series data are dynamic
                 by nature, as in data streams, current solutions to
                 these fundamental problems have been mostly for the
                 static time series databases. In this paper, we first
                 propose a framework to online summary generation for
                 large-scale and dynamic time series data, such as data
                 streams. Then, we propose online transform-based
                 summarization techniques over data streams that can be
                 updated in constant time and space. We present both the
                 exact and approximate versions of the proposed
                 techniques and provide error bounds for the approximate
                 case. One of our main contributions in this paper is
                 the extensive performance analysis. Our experiments
                 carefully evaluate the quality of the online summaries
                 for point, range, and $k ???? nn$ queries using
                 real-life dynamic data sets of substantial size.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data streams; dimensionality reduction; time-series
                 data; transformation-based summarization",
}

@Article{Goh:2006:DBM,
  author =       "Leng Goh and Yanfeng Shu and Zhiyong Huang and Chin
                 Ooi",
  title =        "Dynamic buffer management with extensible replacement
                 policies",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "2",
  pages =        "99--120",
  month =        jun,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:18 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "The objective of extensible DBMSs is to ease the
                 construction of specialized DBMSs for nontraditional
                 applications. Although much work has been done in
                 providing various levels of extensibility (e.g.,
                 extensibility of data types and operators, query
                 language extensibility, and query optimizer
                 extensibility), there has been very limited research in
                 providing extensibility at the buffer management level.
                 Supporting extensibility at the buffer management level
                 is important as it can contribute significantly to
                 overall system performance. This paper addresses the
                 problem of supporting extensibility of buffer
                 replacement policies. The main contribution is the
                 proposal of a framework for modeling buffer replacement
                 policies. This work is novel in two aspects. First, by
                 providing a uniform and generic specification of buffer
                 replacement policies, the proposed framework unifies
                 existing work in this area. Second, our work introduces
                 a new level of extensibility. None of the existing
                 extensible DBMSs, to our knowledge, provides
                 extensibility at the buffer management level. The
                 proposed framework provides a basis for the
                 construction of an extensible buffer manager as part of
                 a 100\% Java-based storage manager. We conducted an
                 extensive performance study to investigate the
                 performance of the proposed framework. The experimental
                 results demonstrate that the proposed framework is
                 indeed feasible for existing DBMSs and improves system
                 performance significantly without costing significant
                 overhead.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "buffer management; extensible DBMS; replacement
                 strategies",
}

@Article{Arasu:2006:CCQ,
  author =       "Arvind Arasu and Shivnath Babu and Jennifer Widom",
  title =        "The {CQL} continuous query language: semantic
                 foundations and query execution",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "2",
  pages =        "121--142",
  month =        jun,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:18 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "{\em CQL}, a {\em continuous query language}, is
                 supported by the STREAM prototype data stream
                 management system (DSMS) at Stanford. CQL is an
                 expressive SQL-based declarative language for
                 registering continuous queries against streams and
                 stored relations. We begin by presenting an abstract
                 semantics that relies only on ``black-box'' mappings
                 among streams and relations. From these mappings we
                 define a precise and general interpretation for
                 continuous queries. CQL is an instantiation of our
                 abstract semantics using SQL to map from relations to
                 relations, window specifications derived from SQL-99 to
                 map from streams to relations, and three new operators
                 to map from relations to streams. Most of the CQL
                 language is operational in the STREAM system. We
                 present the structure of CQL's query execution plans as
                 well as details of the most important components:
                 operators, interoperator queues, synopses, and sharing
                 of components among multiple operators and queries.
                 Examples throughout the paper are drawn from the {\em
                 Linear Road\/} benchmark recently proposed for DSMSs.
                 We also curate a public repository of data stream
                 applications that includes a wide variety of queries
                 expressed in CQL. The relative ease of capturing these
                 applications in CQL is one indicator that the language
                 contains an appropriate set of constructs for data
                 stream processing.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "continuous queries; data streams; query language;
                 query processing",
}

@Article{Hadjieleftheriou:2006:ISA,
  author =       "Marios Hadjieleftheriou and George Kollios and J.
                 Tsotras and Dimitrios Gunopulos",
  title =        "Indexing spatiotemporal archives",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "2",
  pages =        "143--164",
  month =        jun,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:18 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Spatiotemporal objects --- that is, objects that
                 evolve over time --- appear in many applications. Due
                 to the nature of such applications, storing the
                 evolution of objects through time in order to answer
                 historical queries (queries that refer to past states
                 of the evolution) requires a very large specialized
                 database, what is termed in this article a {\em
                 spatiotemporal archive}. Efficient processing of
                 historical queries on spatiotemporal archives requires
                 equally sophisticated indexing schemes. Typical
                 spatiotemporal indexing techniques represent the
                 objects using minimum bounding regions (MBR) extended
                 with a temporal dimension, which are then indexed using
                 traditional multidimensional index structures. However,
                 rough MBR approximations introduce excessive overlap
                 between index nodes, which deteriorates query
                 performance. This article introduces a robust indexing
                 scheme for answering spatiotemporal queries more
                 efficiently. A number of algorithms and heuristics are
                 elaborated that can be used to preprocess a
                 spatiotemporal archive in order to produce {\em finer
                 object approximations}, which, in combination with {\em
                 a multiversion index structure}, will greatly improve
                 query performance in comparison to the straightforward
                 approaches. The proposed techniques introduce a query
                 efficiency vs. space tradeoff that can help tune a
                 structure according to available resources. Empirical
                 observations for estimating the necessary amount of
                 additional storage space required for improving query
                 performance by a given factor are also provided.
                 Moreover, heuristics for applying the proposed ideas in
                 an online setting are discussed. Finally, a thorough
                 experimental evaluation is conducted to show the merits
                 of the proposed techniques.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "indexing; moving objects; spatiotemporal databases;
                 trajectories",
}

@Article{Guting:2006:MQM,
  author =       "Hartmut G{\"u}ting and Teixeira de Almeida and Zhiming
                 Ding",
  title =        "Modeling and querying moving objects in networks",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "2",
  pages =        "165--190",
  month =        jun,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:18 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Moving objects databases have become an important
                 research issue in recent years. For modeling and
                 querying moving objects, there exists a comprehensive
                 framework of abstract data types to describe objects
                 moving freely in the 2D plane, providing data types
                 such as {\em moving point\/} or {\em moving region}.
                 However, in many applications people or vehicles move
                 along transportation networks. It makes a lot of sense
                 to model the network explicitly and to describe
                 movements relative to the network rather than
                 unconstrained space, because then it is much easier to
                 formulate in queries relationships between moving
                 objects and the network. Moreover, such models can be
                 better supported in indexing and query processing. In
                 this paper, we extend the ADT approach by modeling
                 networks explicitly and providing data types for static
                 and moving network positions and regions. In a highway
                 network, example entities corresponding to these data
                 types are motels, construction areas, cars, and traffic
                 jams. The network model is not too simplistic; it
                 allows one to distinguish simple roads and divided
                 highways and to describe the possible traversals of
                 junctions precisely. The new types and operations are
                 integrated seamlessly into the ADT framework to achieve
                 a relatively simple, consistent and powerful overall
                 model and query language for constrained and
                 unconstrained movement.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "ADT; data type; moving object; network;
                 spatio-temporal",
}

@Article{Chirkova:1999:AQU,
  author =       "Rada Chirkova and Chen Li and Jia Li",
  title =        "Answering queries using materialized views with
                 minimum size",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "3",
  pages =        "191--210",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:19 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "In this paper, we study the following problem. Given a
                 database and a set of queries, we want to find a set of
                 views that can compute the answers to the queries, such
                 that the amount of space, in bytes, required to store
                 the viewset is minimum on the given database. (We also
                 handle problem instances where the input has a {\em
                 set\/} of database instances, as described by an oracle
                 that returns the sizes of view relations for given view
                 definitions.) This problem is important for
                 applications such as distributed databases, data
                 warehousing, and data integration. We explore the
                 decidability and complexity of the problem for
                 workloads of conjunctive queries. We show that results
                 differ significantly depending on whether the workload
                 queries have self-joins. Further, for queries without
                 self-joins we describe a very compact search space of
                 views, which contains all views in at least one optimal
                 viewset. We present techniques for finding a
                 minimum-size viewset for a single query without
                 self-joins by using the shape of the query and its
                 constraints, and validate the approach by extensive
                 experiments.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data warehouses; distributed systems; minimum-size
                 viewsets; views",
  remark =       "Check month: April or May??",
}

@Article{Cao:1999:STD,
  author =       "Hu Cao and Ouri Wolfson and Goce Trajcevski",
  title =        "Spatio-temporal data reduction with deterministic
                 error bounds",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "3",
  pages =        "211--228",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:19 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "A common way of storing spatio-temporal information
                 about mobile devices is in the form of a 3D (2D
                 geography + time) trajectory. We argue that when
                 cellular phones and Personal Digital Assistants become
                 location-aware, the size of the spatio-temporal
                 information generated may prohibit efficient
                 processing. We propose to adopt a technique studied in
                 computer graphics, namely line-simplification, as an
                 approximation technique to solve this problem. Line
                 simplification will reduce the size of the
                 trajectories. Line simplification uses a distance
                 function in producing the trajectory approximation. We
                 postulate the desiderata for such a distance-function:
                 it should be sound, namely the error of the answers to
                 spatio-temporal queries must be bounded. We analyze
                 several distance functions, and prove that some are
                 sound in this sense for some types of queries, while
                 others are not. A distance function that is sound for
                 all common spatio-temporal query types is introduced
                 and analyzed. Then we propose an aging mechanism which
                 gradually shrinks the size of the trajectories as time
                 progresses. We also propose to adopt existing
                 linguistic constructs to manage the uncertainty
                 introduced by the trajectory approximation. Finally, we
                 analyze experimentally the effectiveness of
                 line-simplification in reducing the size of a
                 trajectories database.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data reduction; line simplification; moving objects
                 database; uncertainty",
  remark =       "Check month: April or May??",
}

@Article{Benetis:1999:NRN,
  author =       "Rimantas Benetis and S. Jensen and Gytis
                 Kar{\c{c}}iauskas and Simonas {\ocirc{S}}altenis",
  title =        "Nearest and reverse nearest neighbor queries for
                 moving objects",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "3",
  pages =        "229--249",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:19 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "With the continued proliferation of wireless
                 communications and advances in positioning
                 technologies, algorithms for efficiently answering
                 queries about large populations of moving objects are
                 gaining interest. This paper proposes algorithms for
                 $k$ nearest and reverse $k$ nearest neighbor queries on
                 the current and anticipated future positions of points
                 moving continuously in the plane. The former type of
                 query returns $k$ objects nearest to a query object for
                 each time point during a time interval, while the
                 latter returns the objects that have a specified query
                 object as one of their $k$ closest neighbors, again for
                 each time point during a time interval. In addition,
                 algorithms for so-called persistent and continuous
                 variants of these queries are provided. The algorithms
                 are based on the indexing of object positions
                 represented as linear functions of time. The results of
                 empirical performance experiments are reported.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "continuous queries; incremental update; location-based
                 services; mobile objects; neighbor queries; persistent
                 queries",
  remark =       "Check month: April or May??",
}

@Article{Pelleg:1999:DTS,
  author =       "Dan Pelleg and Andrew Moore",
  title =        "Dependency trees in sub-linear time and bounded
                 memory",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "3",
  pages =        "250--262",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:19 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "We focus on the problem of efficient learning of
                 dependency trees. Once grown, they can be used as a
                 special case of a Bayesian network, for PDF
                 approximation, and for many other uses. Given the data,
                 a well-known algorithm can fit an optimal tree in time
                 that is quadratic in the number of attributes and
                 linear in the number of records. We show how to modify
                 it to exploit partial knowledge about edge weights.
                 Experimental results show running time that is
                 near-constant in the number of records, without
                 significant loss in accuracy of the generated trees.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data mining; dependency trees; fast algorithms;
                 probably approximately correct learning",
  remark =       "Check month: April or May??",
}

@Article{Che:1999:QOX,
  author =       "Dunren Che and Karl Aberer and Tamer {\"O}zsu",
  title =        "Query optimization in {XML} structured-document
                 databases",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "3",
  pages =        "263--289",
  month =        apr,
  year =         "1999",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:19 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "While the information published in the form of
                 XML-compliant documents keeps fast mounting up,
                 efficient and effective query processing and
                 optimization for XML have now become more important
                 than ever. This article reports our recent advances in
                 XML structured-document query optimization. In this
                 article, we elaborate on a novel approach and the
                 techniques developed for XML query optimization. Our
                 approach performs heuristic-based algebraic
                 transformations on XPath queries, represented as PAT
                 algebraic expressions, to achieve query optimization.
                 This article first presents a comprehensive set of
                 general equivalences with regard to XML documents and
                 XML queries. Based on these equivalences, we developed
                 a large set of deterministic algebraic transformation
                 rules for XML query optimization. Our approach is
                 unique, in that it performs exclusively deterministic
                 transformations on queries for fast optimization. The
                 deterministic nature of the proposed approach
                 straightforwardly renders high optimization efficiency
                 and simplicity in implementation. Our approach is a
                 logical-level one, which is independent of any
                 particular storage model. Therefore, the optimizers
                 developed based on our approach can be easily adapted
                 to a broad range of XML data/information servers to
                 achieve fast query optimization. Experimental study
                 confirms the validity and effectiveness of the proposed
                 approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "deterministic query optimization; query
                 transformation; XML database; XML query optimization;
                 XML query processing",
  remark =       "Check month: April or May??",
}

@Article{Ferrari:2006:GES,
  author =       "Elena Ferrari and Bhavani Thuraisingham",
  title =        "Guest editorial: special issue on privacy preserving
                 data management",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "4",
  pages =        "291--292",
  month =        nov,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:20 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  remark =       "Check month: April or November??",
}

@Article{Mukherjee:2006:PPT,
  author =       "Shibnath Mukherjee and Zhiyuan Chen and Aryya
                 Gangopadhyay",
  title =        "A privacy-preserving technique for {Euclidean}
                 distance-based mining algorithms using
                 {Fourier}-related transforms",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "4",
  pages =        "293--315",
  month =        nov,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:20 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "Privacy preserving data mining has become increasingly
                 popular because it allows sharing of privacy-sensitive
                 data for analysis purposes. However, existing
                 techniques such as random perturbation do not fare well
                 for simple yet widely used and efficient Euclidean
                 distance-based mining algorithms. Although original
                 data distributions can be pretty accurately
                 reconstructed from the perturbed data, distances
                 between individual data points are not preserved,
                 leading to poor accuracy for the distance-based mining
                 methods. Besides, they do not generally focus on data
                 reduction. Other studies on secure multi-party
                 computation often concentrate on techniques useful to
                 very specific mining algorithms and scenarios such that
                 they require modification of the mining algorithms and
                 are often difficult to generalize to other mining
                 algorithms or scenarios. This paper proposes a novel
                 generalized approach using the well-known energy
                 compaction power of Fourier-related transforms to hide
                 sensitive data values and to approximately preserve
                 Euclidean distances in centralized and distributed
                 scenarios to a great degree of accuracy. Three
                 algorithms to select the most important transform
                 coefficients are presented, one for a centralized
                 database case, the second one for a horizontally
                 partitioned, and the third one for a vertically
                 partitioned database case. Experimental results
                 demonstrate the effectiveness of the proposed
                 approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "data mining; Fourier transform; privacy",
  remark =       "Check month: September or November??",
}

@Article{Jiang:2006:SDF,
  author =       "Wei Jiang and Chris Clifton",
  title =        "A secure distributed framework for achieving
                 {$k$}-anonymity",
  journal =      j-VLDB-J,
  volume =       "15",
  number =       "4",
  pages =        "316--333",
  month =        nov,
  year =         "2006",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Mon Jun 23 10:51:20 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbj.bib",
  abstract =     "$k$-anonymity provides a measure of privacy protection
                 by preventing re-identification of data to fewer than a
                 group of $k$ data items. While algorithms exist for
                 producing $k$-anonymous data, the model has been that
                 of a single source wanting to publish data. Due to
                 privacy issues, it is common that data from different
                 sites cannot be shared directly. Therefore, this paper
                 presents a two-party framework along with an
                 application that generates $k$-anonymous data from two
                 vertically partitioned sources without disclosing data
                 from one site to the other. The framework is privacy
                 preserving in the sense that it satisfies the secure
                 definition commonly defined in the literature of Secure
                 Multiparty Computation.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "http://portal.acm.org/toc.cfm?id=J869",
  keywords =     "anonymity; privacy; security",
  remark =       "Check month: April or November??",
}

@Article{