A new approach to construct membership functions and generate fuzzy rules from training instances

In recent years, many researchers focused on the research topic of constructing fuzzy classification systems to deal with the Iris data classification problem. One of the methods to construct fuzzy classification systems is to construct membership functions at first, and then to generate fuzzy rules. We present a new method to construct membership functions and generate fuzzy rules from training instances based on the correlation coefficient threshold value /spl zeta/, the boundary shift value /spl epsiv/ and the center shift value /spl delta/ to deal with the Iris data classification problem, where /spl zeta/ /spl epsi/ [0, 1], /spl epsiv//spl epsi/ [0, 1] and /spl delta/ /spl epsi/ [0, 1]. The proposed method can get a higher average classification accuracy rate and generates fewer fuzzy rules than the existing methods.