模糊C均值聚类算法的有效性检验研究  

Research on the Validity of Fuzzy C Mean Clustering Algorithm

作　　者：刘来权[1] 陈燕[1] 雷燕瑞[1] LIU Lai-quan;CHEN Yan;LEI Yan-rui(Hainan College of Software Technology, Qionghai 571400, China)

机构地区：[1]海南软件职业技术学院,海南琼海571400

出　　处：《软件》2017年第2期16-18,共3页Software

基　　金：海南省自然科学基金(No.20156232)资助

摘　　要：模糊C均值(Fuzzy C-means,FCM)聚类算法是聚类算法中的经典算法,此算法引入了隶属度及模糊度的概念,应用范围及应用行业也更为广泛。FCM聚类算法的聚类划分受到数据分布的影响较大,模糊度参数的选择很容易影响聚类算法的聚类结果,且易陷入局部极值的问题。因此研究FCM聚类算法的有效性检验方法则具有非常意义。Fuzzy C-means (FCM) clustering algorithm is a classical algorithm in the clustering algorithm, this algorithm introduces the concept of membership and fuzzy degree, the scope of application and the application of the industry is also more extensive C-means. The clustering of FCM clustering algorithm has a great influence on the data distribution,and the selection of fuzzy parameters can easily affect the clustering results of clustering algorithm, and it is easy to fall into the local extremum problem. Therefore, it is of great significance to study the validity of FCM clustering algorithm.

关 键 词：模糊C均值 聚类 有效性 检验 

分 类 号：TP3-0[自动化与计算机技术—计算机科学与技术]