An Efficient Clustering Technique for Message Passing between Data Points using Affinity Propagation

Abstract ─ A wide range of clustering algorithms is available in literature and still an open area for researcher’s k-means algorithm is one of the basic and most simple partitioning clustering technique is given by Macqueen in 1967. A new clustering algorithm used in this paper is affinity propagation. The number of cluster k has been supplied by the user and the Affinity propagation found clusters with much lower error than other methods, and it did so in less than one-hundredth the amount of time between data point. In this paper we make analysis on cluster algorithm k-means, efficient k-means, and affinity propagation with colon dataset. And the result of affinity propagation shows much lower error when compare with other algorithm and the average accuracy is good.