摘要
针对模糊C均值(FCM)聚类算法中,聚类效果往往受到聚类数目和初始聚类中心的影响这一问题,提出了基于平均信息熵确定聚类数目的方法,并采用密度函数法来获得初始聚类中心.实验结果表明,改进后的算法较好地解决了初值问题,与随机初始化方法相比,迭代次数少,收敛速度快.
The performance of fuzzy c - means （FCM） 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. It is shown that the proposed algorithms resolve the inidal problems effectively. Compared with the stochastic initialization, the algorithms have fewer numbers of iterations and have faster speed to converge.
出处
《哈尔滨理工大学学报》
CAS
2007年第4期8-10,共3页
Journal of Harbin University of Science and Technology
关键词
模糊C均值聚类
信息熵
初始化
密度函数
fuzzy C - means clustering
information entropy
initialization
density function
