模糊c-均值聚类算法中加权指数m的研究

A Study of Weighting Exponent m in a Fuzzy c Means Algorithm

加权指数m是模糊c 均值 (FCM)聚类算法中的一个重要参数 .本文从FCM算法出发研究了m对聚类分析的影响 ,m的最佳选取方法及其在聚类有效性中的应用三个问题 .实验结果表明 :m不合适的取值将严重影响算法的性能 ;在实际应用中m的最佳取值范围为 [1 5 ,2 5 ],这与Pal的实验结论相一致 ;另外基于最优加权指数m

Weighting exponent m is an important parameter in fuzzy c means(FCM) algorithm.In this paper,three basic pro blems are studied in FCM algorithm:the effect of m on the performance of fuzzy clustering,the optimal choice of m ,and its preliminary applications in clustering validity.Experimental results indicate that an improper choice of m will influence critically on the performance of clustering,and the optimal range of m is within [1 5,2 5] in the practical applications,which is consistent with the conclusion of Pal.In addition,the approach to determining the optimal number of clusters based on the optimal weighting exponent m * is much effective and sensitive.