A New Cluster Validity Index for Fuzzy Clustering

Cluster validity indices have been used to evaluate the fitness of the partitions produced by the clustering algorithms. In this paper, limiting behavior of some of the existing clustering validity indices are investigated and then a new clustering validity assessment index for fuzzy clusters is proposed which can be used to eliminate the monotonically increasing tendency when the number of clusters c becomes very large and close to the number of data points n. The experimental results indicate the effectiveness of the proposed cluster validity index.