Authors: P. Ganesh Kumar, D. Devaraj
Addresses: Department of Information Technology, Anna University Coimbatore, Jothipuram, Coimbatore 641047, Tamil Nadu, India. ' Department of Electrical and Electronics Engineering, Kalasalingam University, Krishnankoil 626190, Tamil Nadu, India
Abstract: One of the important issues in the design of fuzzy classifier is the formation of fuzzy if-then rules and the membership functions. This paper presents a Genetic Algorithm (GA) approach to obtain the optimal rule-set and the membership function. To develop the fuzzy system the membership functions and rule-set are encoded into the chromosome and evolved simultaneously using GA. Advanced genetic operators are applied to improve the performance of the GA in designing the fuzzy classifier. The performance of the proposed approach is demonstrated through development of fuzzy classifier for Iris, Wine and tcpdump data. From the simulation study, it is found that the improved GA produces a fuzzy classifier which has minimum number of rules and high classification accuracy. Statistical analysis of the test results shows the superiority of the proposed algorithm over the existing methods.
Keywords: fuzzy classifiers; if-then rules; membership function; genetic algorithms; GAs; classifier design; simulation.
International Journal of Computer Applications in Technology, 2009 Vol.35 No.2/3/4, pp.97 - 103
Available online: 20 Jun 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article