ON CLUSTER VALIDITY FOR THE FUZZY C-MEANS MODEL

被引:1310
作者
PAL, NR
BEZDEK, JC
机构
[1] Department of Computer Science, The University of West Florida, Pensacola
关键词
D O I
10.1109/91.413225
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many functionals have been proposed for validation of partitions of object data produced by the fuzzy c-means (FCM) clustering algorithm. We examine the role a subtle but important parameter-the weighting exponent m of the FCM model-plays in determining the validity of FCM partitions, The functionals considered are the partition coefficient and entropy indexes of Bezdek, the Xie-Beni, and extended Xie-Beni indexes, and the Fukuyama-Sugeno index. Limit analysis indicates, and numerical experiments confirm, that the Fukuyama-Sugeno index is sensitive to both high and low values of m and may be unreliable because of this. Of the indexes tested, the Xie-Beni index provided the best response over a wide range of choices for the number of clusters, (2-10), and for m from 1.01-7, Finally, our calculations suggest that the best choice for rn is probably in the interval [1.5, 2.5], whose mean and midpoint, m = 2, have often been the preferred choice for many users of FCM.
引用
收藏
页码:370 / 379
页数:10
相关论文
共 20 条
[1]  
Anderson E, 1935, B AM IRIS SOC, V59, P2
[2]  
[Anonymous], 1974, J CYBERNETICS, DOI [DOI 10.1080/01969727308546047, 10.1080/01969727308546047]
[3]  
BENSAID A, 1994, THESIS U S FLORIDA T
[4]  
Bezdek J.C., 2013, PATTERN RECOGN
[5]  
BEZDEK JC, 1975, 8 INT C NUM TAX SAN, P143
[6]  
BEZDEK JC, 1980, INT J COMPUT INF SCI, V9, P232
[7]  
Bezdek JC, 1973, THESIS CORNELL U ITH
[8]  
Dunn J.C., 1976, FUZZY AUTOMATA DECIS
[9]  
Everitt B. S., 1978, GRAPHICAL TECHNIQUES
[10]  
Fukuyama Y, 1989, 5 FUZZ SYST S, P247