Data Warehousing and Knowledge Discovery: 5th International Conference, DaWaK 2003, Prague, Czech Republic, September 3-5,2003, Proceedings(2737 Lecture Notes in Computer Science)

This book constitutes the refereed proceedings of the 5th International Conference on Data Warehousing and Knowledge Discovery, DaWaK 2003, held in Prague, Czech Republic in September 2003.The 41 revised full papers presented were carefully reviewed and selected from more than 130 submissions. The papers are organized in topical sections on data cubes and queries, multidimensional data models, Web warehousing, change detection, Web mining and association rules, association rules and decision trees, clustering, association rule mining, data analysis and discovery, ontologies and improving data quality, queries and data patterns, improving database query engines, and sampling and vector classification.

Table of Contents:
Invited Talk.- XML for Data Warehousing Chances and Challenges.- Data Cubes and Queries.- CPM: A Cube Presentation Model for OLAP.- Computation of Sparse Data Cubes with Constraints.- Answering Joint Queries from Multiple Aggregate OLAP Databases.- An Approach to Enabling Spatial OLAP by Aggregating on Spatial Hierarchy.- Multidimensional Data Model.- A Multidimensional Aggregation Object (MAO) Framework for Computing Distributive Aggregations.- The GMD Data Model for Multidimensional Information: A Brief Introduction.- An Application of Case-Based Reasoning in Multidimensional Database Architecture.- Web Warehousing.- MetaCube XTM: A Multidimensional Metadata Approach for Semantic Web Warehousing Systems.- Designing Web Warehouses from XML Schemas.- Building XML Data Warehouse Based on Frequent Patterns in User Queries.- Change Detection.- A Temporal Study of Data Sources to Load a Corporate Data Warehouse.- Automatic Detection of Structural Changes in Data Warehouses.- Performance Tests in Data Warehousing ETLM Process for Detection of Changes in Data Origin.- Web Mining and Association Rule.- Recent Developments in Web Usage Mining Research.- Parallel Vector Computing Technique for Discovering Communities on the Very Large Scale Web Graph.- Association Rules and Decision Trees.- Ordinal Association Rules towards Association Rules.- Rough Set Based Decision Tree Model for Classification.- Inference Based Classifier: Efficient Construction of Decision Trees for Sparse Categorical Attributes.- Generating Effective Classifiers with Supervised Learning of Genetic Programming.- Clustering I.- Clustering by Regression Analysis.- Handling Large Workloads by Profiling and Clustering.- Incremental OPTICS: Efficient Computation of Updates in a Hierarchical Cluster Ordering.- Clustering II.- On Complementarity of Cluster and Outlier Detection Schemes.- Cluster Validity Using Support Vector Machines.- FSSM: Fast Construction of the Optimized Segment Support Map.- Association Rule Mining.- Using a Connectionist Approach for Enhancing Domain Ontologies: Self-Organizing Word Category Maps Revisited.- Parameterless Data Compression and Noise Filtering Using Association Rule Mining.- Performance Evaluation of SQL-OR Variants for Association Rule Mining.- Data Analysis and Discovery.- A Distance-Based Approach to Find Interesting Patterns.- Similarity Search in Structured Data.- Ontologies and Improving Data Quality.- Using an Interest Ontology for Improved Support in Rule Mining.- Fraud Formalization and Detection.- Combining Noise Correction with Feature Selection.- Queries and Data Patterns.- Pre-computing Approximate Hierarchical Range Queries in a Tree-Like Histogram.- Comprehensive Log Compression with Frequent Patterns.- Non-recursive Generation of Frequent K-itemsets from Frequent Pattern Tree Representations.- Improving Database Query Engine.- A New Computation Model for Rough Set Theory Based on Database Systems.- Computing SQL Queries with Boolean Aggregates.- Fighting Redundancy in SQL.- Sampling and Vector Classification.- “On-the-fly” VS Materialized Sampling and Heuristics.- Incremental and Decremental Proximal Support Vector Classification using Decay Coefficients.