A self-organizing map with expanding force for data clustering and visualization

Authors

Wing Ho SHUM, Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong
Hui Dong JIN, Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong
Kwong Sak LEUNG, Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong
Man Leung WONG, Department of Information Systems, Lingnan University, Hong Kong

Document Type

Conference paper

Source Publication

Proceedings - IEEE International Conference on Data Mining, ICDM

Publication Date

1-1-2002

First Page

434

Last Page

441

Abstract

The Self-Organizing Map (SOM) is a powerful tool in the exploratory phase of data mining. However, due to the dimensional conflict, the neighborhood preservation cannot always lead to perfect topology preservation. In this paper, we establish an Expanding SOM (ESOM) to detect and preserve better topology correspondence between the two spaces. Our experiment results demonstrate that the ESOM constructs better mappings than the classic SOM in terms of both the topological and the quantization errors. Furthermore, clustering results generated by the ESOM are more accurate than those by the SOM.

DOI

10.1109/ICDM.2002.1183939

Print ISSN

15504786

Publisher Statement

Copyright © 2002 IEEE. Access to external full text or publisher's version may require subscription.

Additional Information

ISBN of the source publication: 9780769517544

Full-text Version

Publisher’s Version

Language

English