Gaussian clustering method based on maximum-fuzzy-entropy interpretation

A new method of fuzzy clustering is proposed. This is a complete Gaussian m embership function derived by means of the maximum-entropy interpretation. Compared to the traditional fuzzy c-means (FCM) method, our approach exhibi ts the following two advantages: (1) having clearer physical meaning and we ll-defined mathematical features; (2) having an optimal choice for feature parameter a in theory. Moreover, we also review some existing measures of u ncertainty of fuzzy sets, and redefine fuzzy entropy as analogous to probab ilistic entropy. (C) 1999 Elsevier Science B.V. All rights reserved.