Analysis of Fuzzy Membership Function Generation with Unsupervised Learning Using Self-Organizing Feature Map

The estimation of membership functions from data is an important step in many applications of fuzzy theory. In this paper, a new scheme is proposed to generate fuzzy membership functions with unsupervised learning using self-organizing feature map. Comparing with some previous literature, in which the self-organizing feature map applies unsupervised learning, is often considered to be a clustering technique. However, the proposed scheme is applied to extract directly the fuzzy membership function during the training and retrieving phases of SOFM. Therefore, our scheme obtained here improve some previously related scheme. Finally, Simulation results support this new scheme.