Authors: Bikram Keshari Mishra; Amiya Kumar Rath
Addresses: Department of Computer Science and Engineering, Veer Surendra Sai University of Technology, Burla, India ' Department of Computer Science and Engineering, Veer Surendra Sai University of Technology, Burla, India
Abstract: There are several aspects on which research works are carried out on clustering. The prime focus is on finding the near optimal cluster centres and determining the best possible clusters. Hence, we have emphasised our work on finding a technique which contemplates on these facets in a way which is far more efficient than several novel approaches. In this paper, we have examined four varieties of clustering algorithms namely; K-Means, FEKM, ECM and proposed FECA implemented on varying data sets. We used few internal cluster validity indices like Dunn's index, Davies-Bouldin's index, Silhouette Coefficient, C index and Calinski index for quantitative evaluation of the clustering results obtained. The results obtained from simulation were compared, and as per our expectation it was found that, the quality of clustering produced by FECA is far more satisfactory than the others. Almost every value of validity indices used give encouraging results for FECA, implying good cluster formation. Further experiments support that the proposed algorithm also produces minimum quantisation error almost for all the data sets used.
Keywords: cluster analysis; cluster validation; optimal centroid; K-means; far efficient K-means; FEKM; far enhanced clustering algorithm; FECA; enhanced clustering methodology; ECM.
International Journal of Data Mining, Modelling and Management, 2018 Vol.10 No.3, pp.269 - 292
Received: 04 Jan 2017
Accepted: 23 Nov 2017
Published online: 08 Aug 2018 *