EFFECTIVE ALGORITHMS FOR THE NEAREST-NEIGHBOR METHOD IN THE CLUSTERING PROBLEM

被引：14

作者：

HATTORI, K

TORII, Y

机构：

[1] Department of Electrical Engineering and Electronics, Toyohashi University of Technology, Toyohashi, 441, Tempaku-cho

来源：

PATTERN RECOGNITION | 1993年 / 26卷 / 05期

关键词：

AGGLOMERATIVE CLUSTERING; NEAREST NEIGHBOR METHOD; SIMILARITY MATRIX; FUZZY CLUSTERING ALGORITHMS; COMPUTATION TIME;

D O I：

10.1016/0031-3203(93)90127-I

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Two effective algorithms are presented for the nearest neighbor method in the hierarchical agglomerative clustering procedures. One is effective, when the number of clusters into which a data set should be classified is already known. The other is effective to search for several probable clustering solutions, when the number of clusters to be obtained is not known in advance. The computation times of the algorithms are shown to be O(N2) for clustering of N objects. Therefore, the algorithms are very powerful for the nearest neighbor method to classify a large data set.

引用

页码：741 / 746

页数：6