SpringerLink Springer Engineering eBooks 2017 English+International

Incluye referencias bibliográficas e índice

Preface -- Chapter 1: Introduction -- Part I: Generalized Related Set Based Approach -- Chapter 2: Information System for Relational Data -- Chapter 3: Properties of Granular-Relational Data Mining Framework -- Chapter 4: Association Discovery and Classification Rule Mining -- Chapter 5: Rough-Granular Computing -- Part II: Description Language Based Approach -- Chapter 6: Compound Information Systems -- Chapter 7: From Granular-Data Mining Framework to its Relational Version -- Chapter 8: Relation-Based Granules -- Chapter 9: Compound Approximation Spaces -- Conclusions -- References -- Index.

This book provides two general granular computing approaches to mining relational data, the first of which uses abstract descriptions of relational objects to build their granular representation, while the second extends existing granular data mining solutions to a relational case. Both approaches make it possible to perform and improve popular data mining tasks such as classification, clustering, and association discovery. How can different relational data mining tasks best be unified? How can the construction process of relational patterns be simplified? How can richer knowledge from relational data be discovered? All these questions can be answered in the same way: by mining relational data in the paradigm of granular computing! This book will allow readers with previous experience in the field of relational data mining to discover the many benefits of its granular perspective. In turn, those readers familiar with the paradigm of granular computing will find valuable insights on its application to mining relational data. Lastly, the book offers all readers interested in computational intelligence in the broader sense the opportunity to deepen their understanding of the newly emerging field granular-relational data mining.