A Novel Fuzzy Cluster Validity Index with New Compositions
Shu Wu, Qingshan Jiang, Zhiling Hong, Shengrui Wang · 2006
Existing indexes are usually composed of two factors: compactness and separation, although some authors use overlap in place of compactness. In this paper, we propose a new index based on a combination of the three factors. This index is potentially more efficient in dealing with simultaneous presence of overlapped clusters, point clusters and low-density clusters. Experimental results support out claim