广义均衡模糊C均值聚类算法

模糊C均值聚类(FCM)算法是一种快速有效的聚类算法,但它没有考虑各类样本容量的差异, 其最小化代价函数会导致聚类判决有利于少样本类.提出一种新的聚类算法—-广义均衡模糊C均值聚类, 通过对模糊C均值聚类最小化代价函数的改进,使得样本容量在聚类代价函数中发挥效用, 从而弱化了样本容量差异对聚类判决的干扰.讨论分析了该算法的性质,模糊隶属度的推导突破了FCM解析解的约束. 通过仿真实验,验证了所提出算法的有效性.

General equalization fuzzy C-means clustering algorithm

Fuzzy C-means clustering (FCM) is a fast and effective clustering algorithm, but it doesn't consider the difference of the samples size, while there exist great difference in the sample capacities of each class, the decision of FCM will be benificial to the class with less samples. A new clustering algorithm was proposed in the paper and named as general equalization fuzzy C-means clustering (GEFCM), GEFCM modified the minimum cost function of FCM and the factor of samples size was embedded in GEFCM cost function, GEFCM weakened the disturbance of sample size difference to clustering decision. The properties of GEFCM was obtained by theoretical analysis, GFECM breaks the restriction which FCM fuzzy membership can only be the distance analytical solution. The effectiveness and robustness of GEFCM are proved through simulation experiments.