Estimation of Fuzzy Regression Parameters With ANFIS and Bayesian Methods

Abstract

In fuzzy regression, estimation of centers and spreads of triangular fuzzy numbers are both performed using the same methods, such as linear programming (LP), quadratic programming (QP), fuzzy weighted linear programming (FWLP), and adaptive neuro-fuzzy inference system (ANFIS). In this article, ANFIS and Bayesian methods have been adopted to estimate centers and spreads of a triangular fuzzy numbers are applied, respectively, for estimation of centers and spreads of the triangular fuzzy data. To illustrate the efficiency of the proposed approach, three numerical examples have been used to verify the superiority of proposed method to other existing ones.