Parameter identification of the fuzzy clusters membership grade functions

Takagi-Sugeno models are an important class of fuzzy rule base oriented models, generally used for prediction and control. Takagi-Sugeno models are data models based on their automatic identification. Fuzzy clustering is one of the effective methods for identification. This paper presents a new method for obtaining the fuzzy sets of input variables using results of fuzzy clustering procedure. The fuzzy set measure of fuzziness is used for determination of the fuzzy set approximation parameters. Results of numerical example are presented to demonstrate the effectiveness of the new proposed method.