A neuro-fuzzy methodology is described which involves connectionist minimization of a fuzzy feature evaluation index with unsupervised training. The concept of a ¯exible membership function incorporating weighed distance is introduced in the evaluation index to make the modeling of clusters more appropriate. A set of optimal weighing coecients in terms of networks parameters representing individual feature importance is obtained through connectionist minimization. Besides, the investigation includes the development of another algorithm for ranking of dierent feature subsets using the aforesaid fuzzy evaluation index without neural networks. Results demonstrating the eectiveness of the algorithms for various real life data are provided. Ó 1998 Published by Elsevier Science B.V. All rights reserved.
Jayanta Basak, Rajat K. De, Sankar K. Pal