A Point Symmetry Distance Based K-Means Algorithm for Distributed Clustering in Peer to Peer Networks

Abstract

In this paper, a distributed K-Means algorithm is proposed based on the point symmetry distance measure which is termed as “Point symmetrical based distributed K-Means (PSDK-Means)” algorithm. Conventional distributed K-Means (DK-Means) clustering is able to detect only spherical shape clusters and it is not suitable for identifying the convex and concave (arbitrary shaped) clusters. The proposed method is implemented to detect spherical, convex and non-convex shape clusters which are distributed over the network at different peers. In the proposed method, cluster centers are shared using the diffusion based cooperation to achieve global clustering of the network. The cluster assignment is carried out using minimum point symmetry distance instead of Euclidean distance. Effectiveness of the proposed PSDK-Means algorithm has been validated on four synthetic and two real life datasets where it is observed to outperform conventional DK-Means algorithm.