反一致可能性C均值聚类算法  

Anti-consistency Possibilistic C-means Clustering Algorithm

作　　者：文传军[1] 汪庆淼[2] 詹永照[3] 

机构地区：[1]常州工学院理学院,常州213002 [2]苏州大学计算机学院,苏州215021 [3]江苏大学计算机科学与通信工程学院,镇江212013

出　　处：《计算机科学》2015年第1期290-292,302,共4页Computer Science

基　　金：国家自然科学基金(61170126);常州工学院校级课题(YN1305)资助

摘　　要：可能性C均值聚类(PCM)因存在聚类中心一致性问题而导致PCM算法聚类失效。提出了反一致可能性C均值聚类算法(ACPCM),它将各聚类中心间距离的倒数之和构造为反一致性项,将反一致性项和PCM目标函数之和构成ACPCM目标函数,利用粒子群算法估计聚类中心,利用梯度法建立模糊隶属度迭代公式。理论分析和仿真实验验证了所提算法的聚类有效性及反一致性。PCM classification judgment will fail while consistency question occurs. A new algorithm was proposed in this paper which is named as anti-consistency possibilistic C-means clustering （ACPCM）. Anti-consistency function is composed of the reciprocal sum of distances between every two clustering centers, and ACPCM objective function is the sum of PCM objective function and anti-consistency function. PSO algorithm is used to estimate clustering centers and gradient method is utilized to solve fuzzy memberships. The effectiveness and anti-consistency of ACPCM were proved through theoretical analysis and simulation experiments.

关 键 词：可能性C均值聚类(PCM) 一致性 聚类中心 粒子群(PSO) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]