An improved Clustering Algorithm based on Fuzzy C-means and Artificial Bee Colony Optimization

Fuzzy C-means (FCM) is considered to be one of the most popular fuzzy clustering techniques. However, it has the limitation of producing bad results due to its search for solution easily getting trapped into local optima. To address this problem a hybrid of FCM and Artificial Bee Colony optimization was proposed in the literature which can give global optimal solutions. This algorithm is also found to have issues such as the dependence of the quality of the results on randomly selected initial cluster centers. Here we propose an improved clustering algorithm based on Fuzzy C-Means and Artificial Bee Colony optimization which involves better methods for finding initial centroids and determining the value of K, the number of clusters.

I. Introduction

Clustering is the task of grouping a set of objects in such a way that the objects in one group are more similar to one another than the objects in other groups. Clustering can be considered as the most important unsupervised learning problem[5]. Clustering is used in exploring data mining, machine learning, pattern recognition, image analysis and data compression [9]. Clustering analysis is not itself an algorithm but it is generally a task which we have to solve.