On K-means data clustering algorithm with genetic algorithm

Abstract

Clustering has been used in various disciplines like software engineering, statistics, data mining, image analysis, machine learning, web cluster engines, and text mining in order to deduce the groups in large volume of data. The notion behind clustering is to ascribe the objects to clusters in such a way that objects in one cluster are more homogeneous to other clusters. There are variegated clustering algorithms available viz k-means clustering, cobweb clustering, db-scan clustering, fartherstfirst clustering, and x-means clustering algorithm but K-means on the whole comprehensively used algorithm for unsupervised clustering dilemma. In this paper k-means clustering is being optimised using genetic algorithm so that the problems of k-means can be overridden. The outcomes of k-means clustering and genetic k-means clustering are evaluated and compared; obtained result shows K-means with GA algorithm suggest new improvements in this research domain.