상세정보

Effective decision support systems (DSS) are quickly becoming key to businesses gaining a competitive advantage, and the effectiveness of these systems depends on the ability to construct, maintain, and extract information from data warehouses. While many still perceive data warehousing as a subdiscipline of management information systems (MIS), in fact many of its advances have and will continue to come from the computer science arena.

Intelligent Data Warehousing presents the state of the art in data warehousing research and practice from a perspective that integrates business applications and computer science. It brings the intelligent techniques associated with artificial intelligence (AI) to the entire process of data warehousing, including data preparation, storage, and mining. Part I provides an overview of the main ideas and fundamentals of data mining, artificial intelligence, business intelligence, and data warehousing. Part II presents core materials on data warehousing, and Part III explores data analysis and knowledge discovery in the data warehousing environment, including how to perform intelligent data analysis and the discovery of influential association patterns.

Bridging the gap between theoretical research and business applications, this book summarizes the main ideas behind recent research developments rather than setting forth technical details, and it presents case studies that show the how-to's of implementing these ideas. The result is a practical, first-of-its-kind book that brings together scattered research, unites MIS with computer science, and melds intelligent techniques with data warehousing.

Intelligent Data Warehousing presents the state of the art in data warehousing research and practice from a perspective that integrates business applications and computer science. It brings the intelligent techniques associated with artificial intelligence (AI) to the entire process of data warehousing. Part I provides an overview of the main ideas and fundamentals of data mining, artificial intelligence, business intelligence, and data warehousing. Part II presents core materials on data warehousing, and Part III explores data analysis and knowledge discovery in the data warehousing environment, including how to perform intelligent data analysis and the discovery of influential association patterns.

정보제공 :

CONTENTS
Part Ⅰ
 Chapter 1 Introduction = 3
  1.1 Why this book is needed = 3
  1.2 Features of the book = 5
  1.3 Why intelligent data warehousing = 5
  1.4 Organization of the book = 6
  1.5 How to use this book = 7
  References = 8
 Chapter 2 Enterprise intelligence and artificial intelligence = 11
  2.1 Overview = 11
  2.2 Data warehousing and enterprise intelligence = 11
  2.3 Historical development of data warehousing = 12
   2.3.1 Prehistory = 12
   2.3.2 Stage 1 : early 1990s = 13
   2.3.3 Stage 2 : mid-1990s = 14
   2.3.4 Stage 3 : toward business intelligence = 14
  2.4 Basic elements of data warehousing = 14
  2.5 Databases and the Web = 15
   2.5.1 World Wide Web and e-commerce = 15
   2.5.2 Data Webhouse = 17
   2.5.3 Ontologies and semantic Web = 20
  2.6 Basics of artificial intelligence and machine learning = 21
   2.6.1 Artificial intelligence as construction of intelligent agents = 21
   2.6.2 State space search and knowledge representation = 22
   2.6.3 Knowledge-based systems = 24
   2.6.4 Symbol-based machine learning = 24
  2.6.5 Genetic algorithms = 25
  2.7 Data warehousing with intelligent agents = 26
   2.7.1 Integration of database and knowledge-based systems = 26
   2.7.2 The role of AI in warehousing = 27
   2.7.3 Java and agent technology = 28
  2.8 Data mining, CRM, Web mining, and clickstream = 29
   2.8.1 What can be analyzed using intelligent data analysis = 29
   2.8.2 From data mining to Web mining = 30
    2.8.2.1 Background = 30
    2.8.2.2 Creating and enhancing Web data = 31
    2.8.2.3 Mining Web data = 31
    2.8.2.4 Other issues of Web mining = 32
    2.8.2.5 Approaches for Web mining = 33
   2.8.3 Clickstream analysis = 33
    2.8.3.1 Components of clickstream analysis = 33
    2.8.3.2 Clickstream data mart = 33
  2.9 The future of data warehouses = 34
  2.10 Summary = 35
  References = 36
 Chapter 3 From DBMS to data warehousing = 39
  3.1 Overview = 39
  3.2 An overview of database management systems = 39
   3.2.1 Data modeling = 39
   3.2.2 Relational data model = 40
   3.2.3 Integrity constraints = 42
   3.2.4 Normalization and normal forms = 43
   3.2.5 Basics of query processing = 43
   3.2.6 Basics of transaction processing = 44
  3.3 Advances in DBMS = 46
   3.3.1 Basics of deductive databases = 46
   3.3.2 Object-relational and object-oriented databases = 47
   3.3.3 Distributed and parallel databases = 47
   3.3.4 Motivations of data warehousing : a technical examination = 48
  3.4 Architecture and design of data warehouses = 52
   3.4.1 Operational systems and warehouse data = 52
   3.4.2 Data warehouse components = 53
   3.4.3 Data warehouse design = 54
  3.5 Data Marts = 55
   3.5.1 Why data marts = 55
   3.5.2 Types of data marts = 56
   3.5.3 Multiple data marts = 57
   3.5.4 Networked data marts = 57
  3.6 Metadata = 58
  3.7 Data warehousing and materialized views = 60
   3.7.1 Materialized views = 60
   3.7.2 Indexing techniques = 62
   3.7.3 Indexing using metadata = 62
  3.8 Data warehouse performance = 64
   3.8.1 Measuring data warehouse performance = 64
   3.8.2 Performance and warehousing activities = 65
  3.9 Data warehousing and OLAP = 66
   3.9.1 Basics of OLAP = 66
   3.9.2 Relationship between data warehousing and OLAP = 67
  3.10 Summary = 68
  References = 68
 Part Ⅱ
 Chapter 4 Data preparation and preprocessing = 73
  4.1 Overview = 73
  4.2 Schema and data integration = 73
  4.3 Data pumping = 75
  4.4 Middleware = 76
  4.5 Data quality = 77
  4.6 Data cleansing = 78
   4.6.1 General aspects of data cleansing = 78
   4.6.2 Data cleansing methods = 79
    4.6.2.1 Domain relevance = 79
    4.6.2.2 Sorted neighborhood duplicate detection method = 80
    4.6.2.3 Multi-pass sorted neighborhood duplicate detection method = 80
    4.6.2.4 Transitive closure = 81
    4.6.2.5 Union-find algorithms = 81
    4.6.2.6 K-way sorting method = 82
  4.7 Dealing with data inconsistency in multidatabase systems = 83
  4.8 Data reduction = 84
  4.9 Case study : data preparation for stock food chain analysis = 85
   4.9.1 Overview = 85
   4.9.2 Preparing the data = 87
    4.9.2.1 Data integration = 88
    4.9.2.2 Data cleaning = 88
    4.9.2.3 Data transformation = 89
    4.9.2.4 Data reduction = 89
    4.9.2.5 SQL query examples = 89
   4.9.3 Building the hierarchies = 91
   4.9.4 Resulting data = 91
  4.10 Web log file preparation = 93
  4.11 Summary = 96
  References = 96
 Chapter 5 Building data warehouses = 97
  5.1 Overview = 97
  5.2 Conceptual data modeling = 97
   5.2.1 Entity-relationship(ER) modeling = 97
   5.2.2 Dimension modeling = 99
  5.3 Data warehouse design using ER approach = 100
   5.3.1 An example = 100
   5.3.2 Steps in using ER model for warehousing conceptual modeling = 102
   5.3.3 Research work on conceptual modeling = 104
  5.4 Aspects of building data warehouses = 105
   5.4.1 Physical design = 105
   5.4.2 Using functional dependencies = 106
   5.4.3 Loading the warehouse = 107
   5.4.4 Metadata management = 107
   5.4.5 Operation phase = 108
   5.4.6 Using data warehouse tools = 108
   5.4.7 User behavior modeling for warehouse design = 109
   5.4.8 Coherent management of warehouses for security = 110
   5.4.9 Prototyping data warehouses = 110
  5.5 Data cubes = 111
  5.6 Summary = 113
  References = 113
 Chapter 6 Basics of materialized views = 117
  6.1 Overview = 117
  6.2 Data cubes = 118
   6.2.1 Materialization of data cubes = 118
   6.2.2 Using the lattice = 121
    6.2.2.1 Hierarchies in lattice = 121
    6.2.2.2 Composite lattices for multiple, hierarchical dimensions = 122
    6.2.2.3 The cost analysis = 123
  6.3 Using a simple optimization algorithm to select views = 125
  6.4 Aggregate calculation using preconstructed data structures in data cubes = 127
   6.4.1 Preliminaries of aggregation functions = 127
   6.4.2 Aggregation operations defined on data cubes = 128
    6.4.2.1 Calculating SUM on data cube using PRE_SUM cube = 128
    6.4.2.2 Calculating COUNT = 129
    6.4.2.3 Calculating MAX by constructing PRE-MAX tree = 130
  6.5 Case study : view selection for a human service data warehouse = 130
   6.5.1 Overview of the case study = 132
   6.5.2 Background information = 133
   6.5.3 Data model = 133
   6.5.4 Queries selected = 134
   6.5.5 Development of the OR view graph = 134
   6.5.6 Implementation = 135
    6.5.6.1 Genetic algorithm description = 136
    6.5.6.2 Solution encoding, reproduction, and mutation = 136
    6.5.6.3 Description of the fitness function = 137
    6.5.6.4 Query benefit function = 138
    6.5.6.5 Penalty function = 138
    6.5.6.6 Total query cost and maintenance cost calculation example = 139
    6.5.6.7 Genetic algorithm implementation = 139
   6.5.7 Resulting views = 139
    6.5.7.1 Small OR view graph = 139
    6.5.7.2 Results from a small view graph = 141
    6.5.7.3 Complete OR view graph = 142
    6.5.7.4 Results from a complete view graph = 143
   6.5.8 Summary of the case study = 144
  6.6 Summary = 145
  References = 145
 Chapter 7 Advances in materialized views = 147
  7.1 Overview = 147
  7.2 Data warehouse design through materialized views = 148
   7.2.1 Data warehouse design = 148
   7.2.2 View selection problem = 148
   7.2.3 View data lineage problem = 150
  7.3 Maintenance of materialized views = 151
   7.3.1 Snapshot differential problem = 151
   7.3.2 Using full and partial information for view maintenance = 151
   7.3.3 Using incremental techniques = 152
   7.3.4 Using auxiliary data and auxiliary views = 153
   7.3.5 Dealing with irrelevant update = 154
   7.3.6 Incremental maintenance of materialized views with duplicates = 154
   7.3.7 Externally materialized views = 155
   7.3.8 Views and queries = 155
   7.3.9 Unified view selection and maintenance = 156
   7.3.10 Other work = 157
  7.4 Consistency in view maintenance = 157
   7.4.1 Immediate and deferred view maintenance = 157
   7.4.2 Dealing with anomalies in view maintenance = 159
   7.4.3 Concurrent updates in distributed environment = 162
  7.5 Integrity constraints and active databases = 163
   7.5.1 Integrity constraints = 163
   7.5.2 Active databases = 164
  7.6 Dynamic warehouse design = 165
   7.6.1 Dynamicity of warehouse design = 165
   7.6.2 Warehouse evolution = 165
   7.6.3 From static to dynamic warehouse design = 166
   7.6.4 View redefinition and adaptation = 167
  7.7 Implementation issues and online updates = 168
   7.7.1 Physical implementation = 168
   7.7.2 Indexing techniques = 168
   7.7.3 Online updates = 168
  7.8 Data cubes = 169
  7.9 Materialized views in advanced database systems = 173
   7.9.1 Materialized views and deductive databases = 173
   7.9.2 Materialized views in object-oriented databases = 174
  7.10 Relationship with mobile databases = 175
  7.11 Other issues = 175
   7.11.1 Temporal view self-maintenance = 175
   7.11.2 Real-time warehousing = 176
   7.11.3 Materialized views in Oracle = 176
  7.12 Summary = 177
  References = 177
Part Ⅲ
 Chapter 8 Intelligent data analysis = 187
  8.1 Overview = 187
  8.2 Basics of data mining = 188
   8.2.1 Categories of data mining = 188
   8.2.2 Association rule mining = 189
   8.2.3 Data classification and characterization = 191
  8.3 Case study : stock food chain analysis = 192
   8.3.1 Overview of the case study = 192
   8.3.2 Implementing the Apriori algorithm = 192
   8.3.3 Graphical user interface = 193
   8.3.4 Analysis = 194
  8.4 Case study : rough set data analysis = 195
   8.4.1 Basics of rough set theory = 195
   8.4.2 Applying RSDA methodology for bankruptcy analysis = 199
    8.4.2.1 Description of the RSDA methodology = 199
    8.4.2.2 Source data used in the case study = 199
    8.4.2.3 Applying RSDA on sample data = 203
  8.5 Recent progress of data mining = 204
   8.5.1 Mining the metadata = 205
   8.5.2 User expectations = 205
   8.5.3 Discovery of low-support rules = 205
   8.5.4 Dynamics of data mining = 205
  8.6 Summary = 206
  References = 206
 Chapter 9 Toward integrated OLAP and data mining = 209
  9.1 Overview = 209
  9.2 Integration of OLAP and data mining = 209
  9.3 Influential association rules = 210
  9.4 Significance of influential association rules = 212
  9.5 Reviews of algorithms for discovery of conventional association rules = 214
  9.6 Discovery of influential association rules = 216
   9.6.1 The IARM algorithm = 216
   9.6.2 Support counting of condition part item set = 217
   9.6.3 Categorization and support counting of a numeric measure = 217
   9.6.4 Mining candidate influential association rules = 218
   9.6.5 Pruning and refining candidate influential association rules = 218
   9.6.6 Problems of the IARM algorithm = 219
  9.7 Bitmap indexing and influential association rules = 220
   9.7.1 Basic idea of bitmap indexing = 220
   9.7.2 Bitmap indexing in data warehouses = 221
  9.8 Mining influential association rules using bitmap indexing(IARMBM) = 223
  9.9 Summary = 226
  References = 226
Index = 229