Enhancement of Parallel K-Means algorithm

This paper mainly focuses on identifying the limitations of the K-Means algorithm and to propose the parallelization of the K-Means using Firefly based clustering method. The new parallel architecture can handle large number of clusters. Modified Firefly algorithm can be used to find initial optimal cluster centroid and then K-Means algorithm with optimized centroid can be used to refine them and improve clustering accuracy. The final convergence issue is also addressed and solved to a great extent. The design methodology is explained in the subsequent sections. Finally, modified algorithm is compared with Parallel K-Means. It is demonstrated with experiments and it has been found that the performance of modified algorithm is better than that of the existing algorithm. Four typical benchmark data sets from the UCI machine learning repository are used to demonstrate the results of the techniques.