Generating Optimal Fuzzy If-Then Rules Using the Partition of Fuzzy Input Space
This paper proposes an extendedfuzzy entropy-based-method for selecting an optimal number of fuzzy rules to construct a compact fuzzy classification system with high classification power. An optimal number of rules are generated through the optimal partition of input space via the extended fuzzy entropy to define an index of feature evaluation in pattern recognition problems decreases as the reliability of a feature in characterizing and discriminating different classes increases. A set of fuzzy if-then rules is coded into a string and treated as an individual in genetic algorithms. The fitness of each individual is specified by the two objectives. The performance of the proposed method for training data and test data is examined by computer simulations on the Mackey-Glass chaotic time series prediction.
Keywordsfuzzy entropy fuzzy input partition genetic algorithm time series
Unable to display preview. Download preview PDF.
- 6.Ichibuchi, H., Watanabe, T.: Learning control by fuzzy models using a simplified fuzzy reasoning. J, Japan Soc. Fuzzy Theory Syst. 2(3), 429–437 (1990)Google Scholar
- 11.Nomura, H., Hayashi, I., Wakami, N.: A self-tuning method of fuzzy reasoning by genetic algorithm. In: Proc. 1992, Int. Fuzzy Syst. Int. Contr. Conf., Louisville, March 16-18, pp. 236–245 (1992)Google Scholar
- 13.Pal, S.K., Chakraborty, B.: Fuzzy set theoretic measure for automatic feature evaluation. IEEE Tran. on SMC, 754–759 (September / October 1986)Google Scholar
- 15.Ichihashi, H.: Iterative fuzzy modeling and a hierarchical network. In: Proc. of the 4th IFSA Congress, Eng., Brussels, pp. 49–52 (1991)Google Scholar
- 16.Araki, D., Nomura, H., Hayashi, I., Wakami, N.: A self generating method of fuzzy inference rules. In: Terano, T., et al. (eds.) Fuzzy Engineering Toward Human Friendly Systems, pp. 1047–1058 (1991)Google Scholar