A monothetic clustering method

被引:72
作者
Chavent, M
机构
[1] Inst Natl Rech Informat & Automat, Act SODAS, F-78153 Le Chesnay, France
[2] Univ Paris 09, Lise Ceremade, F-75775 Paris 16, France
关键词
hierarchical clustering methods; monothetic cluster; inertia criterion;
D O I
10.1016/S0167-8655(98)00087-7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The proposed divisive clustering method performs simultaneously a hierarchy of a set of objects and a monothetic characterization of each cluster of the hierarchy. A division is performed according to the within-cluster inertia criterion which is minimized among the bipartitions induced by a set of binary questions. In order to improve the clustering, the algorithm revises at each step the division which has induced the cluster chosen for division. (C) 1998 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:989 / 996
页数:8
相关论文
共 24 条
[1]  
Anderberg M.R., 1973, Probability and Mathematical Statistics
[2]  
CHAVENT M, 1997, THESIS U PARIS 9 DAU
[3]  
CIAMPI A, 1994, P COMPSTAT 94, P129
[4]   OPTIMIZATION IN NON-HIERARCHICAL CLUSTERING [J].
DIDAY, E .
PATTERN RECOGNITION, 1974, 6 (01) :17-&
[5]  
DIDAY E, 1995, ANN OPER RES, V55, P227
[6]   A METHOD FOR CLUSTER ANALYSIS [J].
EDWARDS, AWF ;
CAVALLIS.LL .
BIOMETRICS, 1965, 21 (02) :362-&
[7]  
Everitt B, 1974, CLUSTER ANAL
[8]  
Friedman JH., 1984, BIOMETRICS, V40, P874, DOI [DOI 10.2307/2530946, 10.2307/2530946]
[9]  
GOWDA KC, 1978, IEEE T SYST MAN CYB, V8, P888
[10]   EFFICIENT ALGORITHMS FOR DIVISIVE HIERARCHICAL-CLUSTERING WITH THE DIAMETER CRITERION [J].
GUENOCHE, A ;
HANSEN, P ;
JAUMARD, B .
JOURNAL OF CLASSIFICATION, 1991, 8 (01) :5-30