This book provides a comprehensive introduction to Rough Set-based feature selection. It enables the reader to systematically study all topics of Rough Set Theory (RST) including the preliminaries, advanced concepts and feature selection using RST. In addition, the book is supplemented with an RST-based API library that can be used to implement several RST concepts and RST-based feature selection algorithms.

Rough Set Theory, proposed in 1982 by Zdzislaw Pawlak, is an area in constant development. Focusing on the classification and analysis of imprecise or uncertain information and knowledge, it has become a prominent tool for data analysis. Feature selection is one of the important applications of RST, and helps us select the features that provide us with the largest amount of useful information.

The book offers a valuable reference guide for all students, researchers, and developers working in the areas of feature selection, knowledge discovery and reasoning with uncertainty, especially those involved in RST and granular computing.

Autorentext

Dr Summair Raza has PhD specialization in Software Engineering from National University of Science and Technology (NUST), Pakistan. He completed his MS from International Islamic University, Pakistan in 2009. He is also associated with Virtual University of Pakistan as Assistant Professor. He has published various papers in international level journals and conferences. His research interests include Feature Selection, Rough Set Theory, Trend Analysis, Software Architecture, Software Design and Non-Functional Requirements.

Dr Usman Qamar has over 15 years of experience in data engineering both in academia and industry. He has Masters in Computer Systems Design from University of Manchester Institute of Science and Technology (UMIST), UK. His MPhil and PhD in Computer Science are from University of Manchester. Dr Qamar's research expertise are in Data and Text Mining, Expert Systems, Knowledge Discovery and Feature Selection. He has published extensively inthese subject areas. His Post PhD work at University of Manchester, involved various data engineering projects which included hybrid mechanisms for statistical disclosure and customer profile analysis for shopping with the University of Ghent, Belgium. He is currently an Assistant Professor at Department of Computer Engineering, National University of Sciences and Technology (NUST), Pakistan and also heads the Knowledge and Data Engineering Research Centre (KDRC) at NUST.

Zusammenfassung

The book will provide:

1. In depth explanation of rough set theory along with examples of the concepts.

2. Detailed discussion on idea of feature selection.

3. Details of various representative and state of the art feature selection techniques along with algorithmic explanations.

4. Critical review of state of the art rough set based feature selection methods covering strength and weaknesses of each.

5. In depth investigation of various application areas using rough set based feature selection.

6. Complete Library of Rough Set APIs along with complexity analysis and detailed manual of using APIs

7. Program files of various representative Feature Selection algorithms along with explanation of each. The book will be a complete and self-sufficient source both for primary and secondary audience. Starting from basic concepts to state-of-the art implementation, it will be a constant source of help both for practitioners and researchers. Book will provide in-depth explanation of concepts supplemented with working examples to help in practical implementation. As far as practical implementation is concerned, the researcher/practitioner can fully concentrate on his/her own work without any concern towards implementation of basic RST functionality.

Providing complexity analysis along with full working programs will further simplify analysis and comparison of algorithms.

Inhalt

Introduction to Feature Selection.- Background.- Rough Set Theory.- Advance Concepts in RST.- Rough Set Based Feature Selection Techniques.- Unsupervised Feature Selection using RST.- Critical Analysis of Feature Selection Algorithms.- RST Source Code.