Fuzzy least-squares algorithms for interactive fuzzy linear regression models

Fuzzy regression analysis can be thought of as a fuzzy variation of classical regression analysis. It has been widely studied and applied in diverse areas. In general, the analysis of fuzzy regression models can be roughly divided into two categories. The first is based on Tanaka's linear-programming approach. The second category is based on the fuzzy least-squares approach. In this paper, new types of fuzzy least-squares algorithms with a noise cluster for interactive fuzzy linear regression models are proposed. These algorithms are robust for the estimation of fuzzy linear regression models, especially when outliers are present. Numerical examples are given to detail the effectiveness of this approach. (C) 2002 Elsevier Science B.V. All rights reserved.