A Comparative Study of Fuzzy C-Means Algorithm and Entropy-Based Fuzzy Clustering Algorithms

Abstract

Fuzzy clustering is useful to mine complex and multi-dimensional data sets, where the members have partial or fuzzy relations. Among the various developed techniques, fuzzy-C-means (FCM) algorithm is the most popular one, where a piece of data has partial membership with each of the pre-defined cluster centers. Moreover, in FCM, the cluster centers are virtual, that is, they are chosen at random and thus might be out of the data set. The cluster centers and membership values of the data points with them are updated through some iterations. On the other hand, entropy-based fuzzy clustering (EFC) algorithm works based on a similarity-threshold value. Contrary to FCM, in EFC, the cluster centers are real, that is, they are chosen from the data points. In the present paper, the performances of these algorithms have been compared on four data sets, such as IRIS, WINES, OLITOS and psychosis (collected with the help of forty doctors), in terms of the quality of the clusters (that is, discrepancy factor, compactness, distinctness) obtained and their computational time. Moreover, the best set of clusters has been mapped into 2-D for visualization using a self-organizing map (SOM).