TreeSOM: Cluster analysis in the self-organizing map

被引：27

作者：

Samsonova, Elena V.

Kok, Joost N.

IJzerman, Ad P.

机构：

[1] Leiden Univ, Div Med Chem, Leiden Amsterdam Ctr Drug Res, NL-2333 CC Leiden, Netherlands

[2] Leiden Univ, Leiden Inst Adv Comp Sci, NL-2333 CA Leiden, Netherlands

来源：

NEURAL NETWORKS | 2006年 / 19卷 / 6-7期

关键词：

self-organizing map; hierarchical clustering; tree; reliability; visualization; tool;

D O I：

10.1016/j.neunet.2006.05.003

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Clustering problems arise in various domains of science and engineering. A large number of methods have been developed to date. The Kohonen self-organizing map (SOM) is a popular tool that maps a high-dimensional space onto a small number of dimensions by placing similar elements close together, forming clusters. Cluster analysis is often left to the user. In this paper we present the method TreeSOM and a set of tools to perform unsupervised SOM cluster analysis, determine cluster confidence and visualize the result as a tree facilitating comparison with existing hierarchical classifiers. We also introduce a distance measure for cluster trees that allows one to select a SOM with the most confident clusters. (c) 2006 Elsevier Ltd. All rights reserved.

引用

页码：935 / 949

页数：15

共 28 条

[1]

[Anonymous], 1997, SPRINGER SERIES INFO

[2]

[Anonymous], P ISBM 96 INT SYST M

[3]

Blake C.L., 1998, UCI repository of machine learning databases

[4] Uncovering hierarchical structure in data using the growing hierarchical self-organizing map [J].