An introduction to type-2 TSK fuzzy logic systems

Type-2 fuzzy sets allow one to handle linguistic uncertainties. This paper presents the architectures of three type-2 TSK fuzzy logic systems (FLSs). There are three because of the possible type-1 or type-2 natures of the antecedent memberships and parameters of the consequent. The output of a type-2 TSK FLS is a type-1 set (which can be defuzzified), whereas the output of a type-1 TSK FLS is a crisp number (type-0 set). Simulation results are provided that compare the outputs of type-2 and type-1 TSK FLSs.