Type2 TSK Fuzzy Logic System and its Type1 Counterpart

Abstract

An interval type2 TSK fuzzy logic system can be obtained by considering the membership functions of its existed type1 counterpart as primary membership functions and assigning uncertainty to cluster centers, standard deviation of Gaussian membership functions and consequence parameters. In many cases it has been difficult to determine the spread percentages for these parameters to obtain an optimal model. In order to develop robust and reliable solutions for the problems, this paper distinguishes the differences between type2 TSK system and its counterpart, analyzes the sensibility of the outputs of a type2 TSK fuzzy system, and discusses the approximation capacities of type2 TSK FLS and its type1 counterpart as well.