A Weighted Sum Validity Function for Clustering With BPSO Algorithm

In this paper, we suggest an objective function called the weighted sum validity function (WSVF), which is a weighted sum of the several normalized cluster validity functions. Further, a binary particle swarm optimization (BPSO) approach is proposed for automatically constructing the proper number of clusters as well as appropriate partitioning of the data set. And we hybridize the BPSO method with the k-means algorithm to optimize the WSVF automatically. In the experiments, we show the effectiveness of the WSVF and the validity of the BPSO. The BPSO can consistently and efficiently converge to the optimum corresponding to the given data in concurrence with the convergence result. The WSVF is found generally able to improve the confidence of clustering solutions and achieve more accurate and robust results.