Chameleon: Hierarchical clustering using dynamic modeling

被引:1250
作者
Karypis, G [1 ]
Han, EH [1 ]
Kumar, V [1 ]
机构
[1] Univ Minnesota, Dept Comp Sci & Engn, Minneapolis, MN 55455 USA
关键词
D O I
10.1109/2.781637
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Many advanced algorithms have difficulty dealing with highly variable clusters that do not follow a preconceived model. By basing its selections on both interconnectivity and closeness, the Chameleon algorithm yields accurate results for these highly variable clusters.
引用
收藏
页码:68 / +
页数:9
相关论文
共 12 条
[1]  
BOLEY D, 1999, IN PRESS AI REV
[2]   Data mining: An overview from a database perspective [J].
Chen, MS ;
Han, JW ;
Yu, PS .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1996, 8 (06) :866-883
[3]   Clustering large datasets in arbitrary metric spaces [J].
Ganti, V ;
Ramakrishnan, R ;
Gehrke, J ;
Powell, A ;
French, J .
15TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING, PROCEEDINGS, 1999, :502-511
[4]  
GOWDA KC, 1978, PATTERN RECOGN, V10, P105
[5]  
Guha S., 1998, SIGMOD Record, V27, P73, DOI 10.1145/276305.276312
[6]   ROCK: A robust clustering algorithm for categorical attributes [J].
Guha, S ;
Rastogi, R ;
Shim, K .
15TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING, PROCEEDINGS, 1999, :512-521
[7]  
HAN EH, 1997, TR97019 U MINN DEPT
[8]  
HAN EH, 1998, B TECHNICAL COMMITTE, V21, P15
[9]  
Jain K, 1988, Algorithms for clustering data
[10]  
Karypis G., 1998, hMETIS 1.5: A hypergraph partitioning package