A type-2 neuro-fuzzy system based on clustering and gradient techniques applied to system identification and channel equalization

Abstract

The integration of fuzzy systems and neural networks has recently become a popular approach in engineering fields for modelling and control of uncertain systems. This paper presents the development of novel type-2 neuro-fuzzy system for identification of time-varying systems and equalization of time-varying channels using clustering and gradient algorithms. It combines the advantages of type-2 fuzzy systems and neural networks. The type-2 fuzzy system allows handling the uncertainties associated with information or data in the knowledge base of the process. The structure of the proposed type-2 TSK fuzzy neural system (FNS) is given and its parameter update rule is derived, based on fuzzy clustering and gradient learning algorithm. The proposed structure is used for identification and noise equalization of time-varying systems. The effectiveness of the proposed system is evaluated by comparing the results obtained by the use of models seen in the literature.