A Clustering Algorithm Based on Trust Values

For the shortage of K-Means algorithm, a clustering algorithm based on trust value called TrustCluster is proposed, The algorithm does not need to pre-specify the number of clusters, and clustering results do not depend on the selection of the initial values, clusters of nonspherical shape can be found and the outliers can be identified effectively . TrustCluster clustering algorithm was verified on the real data and artificial data, and compared with the K-Means and Voting-K-Means algorithms, the result showed that TrustCluster algorithm is feasible and effective.