Fuzzy order statistics and their application to fuzzy clustering

被引：62
作者：
Kersten, PR [1 ]
机构：
[1] Midwestern State Univ, Dept Comp Sci, Wichita Falls, TX 76308 USA
来源：
IEEE TRANSACTIONS ON FUZZY SYSTEMS | 1999年 / 7卷 / 06期
关键词：
FCM; FCMED; fuzzy sets; MAD;
D O I：
10.1109/91.811239
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The median and the median absolute deviation (MAD) are robust statistics based on order statistics. Order statistics are extended to fuzzy sets to define a fuzzy median and a fuzzy MAD. The fuzzy c-means (FCM) clustering algorithm is defined for any p-norm (pPCM), including the l(1)-norm (1FCM). The 1FCM clustering algorithm is implemented via the alternating optimization (AO) method and the clustering centers are shown to be the fuzzy median. The resulting AO-1FCM clustering algorithm is called the fuzzy c-medians (FCMED) clustering algorithm. An example illustrates the robustness of the FCMED.
引用
收藏
页码：708 / 712
页数：5
相关论文
共 25 条
[1]  
[Anonymous], Pattern Recognition With Fuzzy Objective Function Algorithms
[2]  
Bezdek JC., 1992, FUZZY MODELS PATTERN
[3]  
Birkes D., 1993, ALTERNATIVE METHODS, DOI 10.1002/9781118150238
[4]  
Bloomfield P., 1983, LEAST ABSOLUTE DEVIA
[5]   C-MEANS CLUSTERING WITH THE L1 AND L-INFINITY NORMS [J].
BOBROWSKI, L ;
BEZDEK, JC .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1991, 21 (03) :545-554
[6]  
CORMAN T, 1989, INTRO ALGORITHMS
[7]  
DOUGHERTY E, 1994, SPIE OPT ENG TT, V16
[8]  
Edgeworth F, 1887, PHILOS MAG, V24, P222
[9]  
Engemann K. J., 1995, Proceedings of ISUMA - NAFIPS '95 The Third International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society (Cat. No.95TB8082), P9, DOI 10.1109/ISUMA.1995.527661
[10]  
Gibbons J. D., 1971, NONPARAMETRIC STAT I
123