E-Means: An Evolutionary Clustering Algorithm

Abstract

In this paper we propose a new evolutionary clustering algorithm named E-means. E-means is an Evolutionary extension of k-means algorithm that is composed by a revised k-means algorithm and an evolutionary approach to Gaussian mixture model, which estimates automatically the number of clusters and the optimal mean for each cluster. More specifically, the proposed E-means algorithm defines an entropy-based fitness function, and three genetic operators for merging, mutation, and deletion components. We conduct two sets of experiments using a synthetic dataset and an existing benchmark to validate the proposed E-means algorithm. The results obtained in the first experiment show that the algorithm can estimate exactly the optimal number of clusters for a set of data. In the second experiment, we compute nine major clustering validity indices and compare the corresponding results with those obtained using four established clustering techniques, and found that our E-means algorithm achieves better clustering structures.