基于遗传算法的模糊聚类分析  

Genetic Algorithm Based on Fuzzy Cluster Analysis

作　　者：宫尚宝[1] 郭玉翠[1] 

机构地区：[1]北京邮电大学理学院,北京100876

出　　处：《模糊系统与数学》2010年第6期123-128,共6页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金资助项目(60973146)

摘　　要：针对模糊C-均值算法容易收敛于局部极小点的缺陷,将遗传算法应用于算法的优化计算。同时针对算法中,聚类效果往往受到聚类数目和初始聚类中心的影响,提出了基于平均信息熵确定聚类数目的方法,并采用密度函数来获得初始聚类中心。实验证明,基于遗传算法的模糊聚类方法能够避免产生局部极小值,较好的解决聚类结果对初值的依赖。This paper applies genetic arithmetic to optimization of the fuzzy c-mean arithmetic since the fuzzy c-mean arithmetic has the limitation of converging to the local infinitesimal point.The performance of fuzzy c-means clustering algorithm depends on the selection of the number of clusters and the initial cluster centers.To answer the two questions,this paper puts forward a new algorithm based on the average information entropy to find the number of clusters and adopts a density function algorithm to find the initial cluster centers.The experiments prove that the fuzzy c-means arithmetic based on genetic arithmetic can overcome the influence of initial values and possess the predominance in the clustering of huge samples.

关 键 词：模糊聚类 遗传算法 信息熵 FCM 

分 类 号：O159[理学—数学]