Publications

Soft Computing for Knowledge Discovery: Introducing Cartesian
Granule Features

Kluwer International Series in Engineering and Computer Science
(Volume 570)

BY James G. Shanahan
FOREWORD BY Lotfi Zadeh

http://www.wkap.nl/book.htm/0-7923-7918-7
http://www.amazon.co.uk/exec/obidos/ASIN/0792379187/

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. na�ve 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.

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.

Used as course material for:
- University of Cincinnati (see webpage
http://www.ececs.uc.edu/~aralescu/Previous_Courses/690/690syll.html)

Kluwer will offer a special PROMOTION on this book starting today,
Monday, March 26th, 2001. The discount price is 28% -
USD 97.00, EUR 111.24, GBP 68.40.

James G. Shanahan PhD, a researcher at the Grenoble Laboratory of the
Xerox Research Centre Europe (XRCE), has published numerous papers at
international conferences, workshops and journals on fuzzy set theory,
machine learning, machine vision, and genetic programming.  A member of
the program committee in several international conferences and workshops
in the field of fuzzy logic and genetic programming, his research
interests are in the inter-disciplinary fields of machine learning and
knowledge discovery, using problem solving strategies such as
probability and statistics, fuzzy set theory, fuzzy logic, and genetic
programming/algorithms, and in application domains such as image
understanding and text mining.