Soft Computing for Knowledge Discovery

Introducing Cartesian Granule Features

  • James G. Shanahan

Table of contents

  1. Front Matter
    Pages i-xxi
  2. Knowledge Discovery

    1. Front Matter
      Pages 1-1
    2. James G. Shanahan
      Pages 3-19
  3. Knowledge Representation

    1. Front Matter
      Pages 21-21
    2. James G. Shanahan
      Pages 23-34
    3. James G. Shanahan
      Pages 35-66
    4. James G. Shanahan
      Pages 67-91
    5. James G. Shanahan
      Pages 93-127
    6. James G. Shanahan
      Pages 129-139
  4. Machine Learning

    1. Front Matter
      Pages 141-141
    2. James G. Shanahan
      Pages 143-175
  5. Cartesian Granule Features

    1. Front Matter
      Pages 177-177
    2. James G. Shanahan
      Pages 179-197
    3. James G. Shanahan
      Pages 199-237
  6. Applications

    1. Front Matter
      Pages 239-239
    2. James G. Shanahan
      Pages 241-280
    3. James G. Shanahan
      Pages 281-314
  7. Back Matter
    Pages 315-326

About this book


Knowledge discovery is an area of computer science that attempts to uncover interesting and useful patterns in data that permit a computer to perform a task autonomously or assist a human in performing a task more efficiently.
Soft Computing for Knowledge Discovery provides a self-contained and systematic exposition of the key theory and algorithms that form the core of knowledge discovery from a soft computing perspective. It focuses on knowledge representation, machine learning, and the key methodologies that make up the fabric of soft computing - fuzzy set theory, fuzzy logic, evolutionary computing, and various theories of probability (e.g. naïve Bayes and Bayesian networks, Dempster-Shafer theory, mass assignment theory, and others). In addition to describing many state-of-the-art soft computing approaches to knowledge discovery, the author introduces Cartesian granule features and their corresponding learning algorithms as an intuitive approach to knowledge discovery. This new approach embraces the synergistic spirit of soft computing and exploits uncertainty in order to achieve tractability, transparency and generalization. Parallels are drawn between this approach and other well known approaches (such as naive Bayes and decision trees) leading to equivalences under certain conditions.
The approaches presented are further illustrated in a battery of both artificial and real-world problems. Knowledge discovery in real-world problems, such as object recognition in outdoor scenes, medical diagnosis and control, is described in detail. These case studies provide further examples of how to apply the presented concepts and algorithms to practical problems.
The author provides web page access to an online bibliography, datasets, source codes for several algorithms described in the book, and other information.
Soft Computing for Knowledge Discovery is for advanced undergraduates, professionals and researchers in computer science, engineering and business information systems who work or have an interest in the dynamic fields of knowledge discovery and soft computing.


Bayesian network algorithms cognition computer science evolution fuzzy fuzzy logic information system knowledge knowledge discovery knowledge representation learning machine learning probability uncertainty

Authors and affiliations

  • James G. Shanahan
    • 1
  1. 1.Xerox Research Centre Europe (XRCE)Grenoble LaboratoryMeylanFrance

Bibliographic information

  • DOI
  • Copyright Information Kluwer Academic Publishers 2000
  • Publisher Name Springer, Boston, MA
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4613-6947-9
  • Online ISBN 978-1-4615-4335-0
  • Series Print ISSN 0893-3405
  • Buy this book on publisher's site
Industry Sectors
Finance, Business & Banking
IT & Software
Energy, Utilities & Environment