Using Swarm Intelligence Approach in the Optimal Design of Fuzzy Rule-Based Classifier Systems

Document Type : Persian Original Article

Authors

1 Department of Electrical Engineering, University of Birjand, Birjand, Iran.

2 Department of Electrical and Computer Engineering, Faculty of Engineering, University of Birjand, Shoukat-Abad, Birjand, Iran.

Abstract

Fuzzy classifiers as a kind of fuzzy systems are powerful approaches in pattern recognition
tasks. These classifiers consist of various structural parameters, each of them have major effects
on the performance of fuzzy classifiers. Type and locations of membership functions, in addition
to fuzzy antecedents and consequents are most important of these structural parameters.
Usually, the major problem in design and implementation of fuzzy classifiers is optimum setting
up of these parameters, to reach the best performance. In this paper, a method is described for
estimation of optimum aforementioned fuzzy parameters in a fuzzy classifier. Extensive
experimental results are presented to show the effectiveness and powerfulness of the proposed
method.

Keywords

Journal of Soft Computing and Information Technology
Volume 1, Issue 1 - Serial Number 1
January 2011
Pages 89-100

Files

Share

How to cite

Statistics