CHSMST:A Clustering algorithm based on hyper surface and Minimum Spanning Tree
Qing He, Weizhong Zhao, Zhongzhi Shi · 2008
Firstly, a new Clustering algorithm based on Hyper Surface (CHS) is put forward in this paper. CHS needs no domain knowledge to determine input parameters. However, it is difficult to process locally dense data for CHS. Then, an efficient clustering algorithm CHSMST is proposed, which is based on CHS and Minimum Spanning Tree. In the first step, CHSMST applies CHS to obtain initial clusters. After interacting, minimum spanning tree is introduced to handle locally dense data with which it is hard for CHS to deal. The experiments show that CHSMST can discover clusters with arbitrary shape. Moreover, the run time of CHSMST increases moderately as the scale of data set becomes large.