Developing Multi-Database Mining Applications

Chapter 1: Introduction 1.1 Motivation 1.2 Distributed Data Mining 1.3 Existing Multi-database Mining Approaches 1.4 Applications of Multi-database Mining 1.5 Improving Multi-database Mining 1.6 Future Directions Chapter 2: An Extended Model of Local Pattern Analysis 2.1 Introduction 2.2 Some Extreme Types of Association Rules in Multiple Databases 2.3 An Extended Model of Local Pattern Analysis for Synthesizing Global Patterns from Local Patterns in Different Databases 2.4 An Application: Synthesizing Heavy Association Rules in Multiple Real Databases 2.5 Conclusions Chapter 3: Mining Multiple Large Databases 3.1 Introduction 3.2. Multi-database Mining Using Local Pattern Analysis 3.3. Generalized Multi-database Mining Techniques 3.4. Specialized Multi-database Mining Techniques 3.5. Mining Multiple Databases Using Pipelined Feedback Model (PFM) 3.6. Error Evaluation 3.7. Experiments 3.8. Conclusions Chapter 4: Mining Patterns of Select Items in Multiple Databases 4.1 Introduction 4.2 Mining Global Patterns of Select Items 4.3 Overall Association Between Two Items in a Database 4.4 An Application: Study of Select Items in Multiple Databases by Grouping 4.5 Related work 4.6 Conclusions Chapter 5: Enhancing Quality of Knowledge Synthesized from Multi-database Mining 5.1 Introduction 5.2 Related work 5.3. Simple Bit Vector (SBV) Coding 5.4 Antecedent-consequent Pair (ACP) Coding 5.5 Experiments 5.6 Conclusions Chapter 6: Efficient Clustering of Databases Induced by Local Patterns 6.1 Introduction 6.2 Problem Statement 6.3 Related Work 6.4 Clustering Databases 6.5 Experiments 6.6 Conclusions Chapter 7: A Framework for Developing Effective Multi-database Mining Applications 7.1 Introduction 7.2 Shortcomings of Existing Approaches to Multi-database Mining 7.3 Improving Multi-database Mining Applications 7.4 Conclusions References Index