基于类内差异和类间重叠的有效性函数  

A new validity index based on intra-cluster variation and inter-cluster overlap

作　　者：贲圣兰[1] 苏光大[1] 

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《光电子．激光》2010年第2期298-302,共5页Journal of Optoelectronics·Laser

基　　金：国家"十一五"科技支撑计划资助项目(2006BAK08B07)

摘　　要：模糊C-均值(FCM)聚类算法的一个主要问题是需要事先确定聚类的数目,为此定义了类内差异度和类间重叠度来分别度量同一个聚类中数据的相似度和不同聚类间的分离程度,进而基于这两个度量提出一个新的有效性函数用于判定最佳聚类数目。实验结果表明,该有效性函数能有效地判定聚类数目,并且有较好的鲁棒性。The determination of cluster number is still an open problem for fuzzy C-means clustering.In this paper,a new validity index is proposed to evaluate partition and determine the optimal number of clusters for fuzzy clustering.In a good partition,the similarities of patterns in a cluster should be maximized and the clusters should be well separated.Intra-cluster variation and intercluster overlap are defined to measure the similarities within a cluster and the separation between clusters respectively.The validity index is defined based on the two measurements.Experimental results on four artificial datasets and two real datasets show the effectiveness and robustness of the proposed validity index.

关 键 词：聚类 模糊C-均值(FCM)聚类 有效性函数 类内差异度 类间重叠度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]