1. Data Processing and KDD. - 1. 1 Inductive Learning from Observation. - 1. 2 Knowledge Discovery and Data Mining. - 1. 3 Feature Selection and Its Roles in KDD. - 1. 4 Summary. - References. - 2. Perspectives of Feature Selection. - 2. 1 Feature Selection for Classification. - 2. 2 A Search Problem. - 2. 3 Selection Criteria. - 2. 4 Univariate vs. Multivariate Feature Selection. - 2. 5 Filter vs. Wrapper Models. - 2. 6 A Unified View. - 2. 7 Conclusion. - References. - 3. Aspects of Feature Selection. - 3. 1 Overview. - 3. 2 Basic Feature Generation Schemes. - 3. 3 Search Strategies. - 3. 4 Evaluation Measures With Examples. - 3. 5 Conclusion. - References. - 4. Feature Selection Methods. - 4. 1 Representative Feature Selection Algorithms. - 4. 2 Employing Feature Selection Methods. - 4. 3 Conclusion. - References. - 5. Evaluation and Application. - 5. 1 Performance Assessment. - 5. 2 Evaluation Methods for Classification. - 5. 3 Evaluation of Selected Features. - 5. 4 Evaluation: Some Examples. - 5. 5 Balance between Different Performance Criteria. - 5. 6 Applying Feature Selection Methods. - 5. 7 Conclusions. - References. - 6. Feature Transformation and Dimensionality Reduction. - 6. 1 Feature Extraction. - 6. 2 Feature Construction. - 6. 3 Feature Discretization. - 6. 4 Beyond the Classification Model. - 6. 5 Conclusions. - References. - 7. Less is More. - 7. 1 A Look Back. - 7. 2 A Glance Ahead. - References. - Appendices. - A-Data Mining and Knowledge Discovery Sources. - A. 1 Web Site Links. - A. 2 Electronic Newsletters Pages and Journals. - A. 3 Some Publically Available Tools. - B-Data Sets and Software Used in This Book. - B. 1 Data Sets. - B. 2 Software. - References. Language: English