基于最优分类系数及分类熵准则的模糊c均值聚类算法  

A Fuzzy c-Means Algorithm with the Criterion of Optimal Partition Coefficient and Entropy

作　　者：郑小松[1] 王绍霖[1] 

机构地区：[1]同济大学电气工程系

出　　处：《电子学报》1994年第7期84-88,共5页Acta Electronica Sinica

摘　　要：本文分别以模糊分类系数和分类熵为聚类有效性的测度函数，采用模糊Ｃ均值分类法，求最优的测度函数值所代表的全局极值的那种分类。确定为最佳分类方式；并对一张由卫星拍摄的地面ＭＩＧ－２９型飞机照片进行了成功的分类试验。This correspondence states the criterion of cluster validity problem which injects validity measurement functionals into the final judgement i such as fuzzy partition coefficient and entropy.It involves the optimizing of validity functionals through the implementation of FCM algorithm to evaluate optimal clustering.In this way,a unique global minimum can be guaranteed for validity functional over fuzzy c-partition space.A clustering experiment for recognition of an ambiguous photograph of MIG- 29 fighter taken by a spy satellite is successfully developed by computer simulation.

关 键 词：模糊聚类 模糊熵 模式识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]