An optimized clustering method with improved cluster center for social network based on gravitational search algorithm

Abstract

Data clustering is a kind of data analysis techniques for grouping the set of data objects into clusters. To make use of the advantages of distance measure and nearest neighbor method, we present a hybrid data clustering algorithm based on GSA and DPC (GSA-DPC) algorithm. The optional clustering center set is selected by DPC algorithm. In turn, we optimize the clustering center set to achieve the best clustering distribution under the fame of GSA. Its performance is compared with four related clustering algorithms. The simulation results demonstrate the effectiveness of the presented algorithm.