A New Cluster Validity Index for The Fuzzy C-mean Method
Clustering is the unsupervised extraction of groups from an unlabelled data set with no prior knowledge of the underlying data structure. Fuzzy Cmeans (FCM) is one of the most widely used fuzzy clustering algorithms in real world applications. However there is a major limitation that exists in this method. A predefined number of clusters must be given in advance. Many fuzzy partition validity indices have been proposed for evaluating clustering results. In this paper, we propose a new validity index to deal with this situation. The performance evaluation of the proposed cluster validity index compares favorably with that of several validity functions and shows the effectiveness.
Jiesheng Wang Yong Zhang
School of Electronic and Information Engineering Liaoning University of Science & Technology Anshan, 114044 China
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）