Topographic measure based on external criteria for self-organizing map

Authors:
Ken-ichi Fukui;Masayuki Numao
Affiliations:
The Institute of Scientific and Industrial Research (ISIR), Osaka University, Osaka, Japan;The Institute of Scientific and Industrial Research (ISIR), Osaka University, Osaka, Japan
Venue:
WSOM'11 Proceedings of the 8th international conference on Advances in self-organizing maps
Year:
2011

Citing 4
Cited 0

Self-Organizing Maps

Self-Organizing Maps
Mining massive document collections by the WEBSOM method

Information Sciences: an International Journal - Special issue: Soft computing data mining
Entropy-Based Measures for Clustering and SOM Topology Preservation Applied to Content-Based Image Indexing and Retrieval

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Kullback-Leibler Divergence Based Kernel SOM for Visualization of Damage Process on Fuel Cells

ICTAI '10 Proceedings of the 2010 22nd IEEE International Conference on Tools with Artificial Intelligence - Volume 01

Quantified Score

Hi-index	0.00

Visualization

Abstract

We proposed the methodology of introducing topographic component to conventional clustering measures for the evaluation of the SOM using external criteria, i.e., class information. The topographic measure evaluates clustering accuracy together with topographic connectivity of class distribution on the topology space of the SOM. The topographic component is introduced by marginalization of basic statistics to the set-based measures, and by a likelihood function to the pairwisebased measures. Our method can extend any clustering measure based on set or pairwise of data points. The present paper examined the topographic component of the extended measure and revealed an appropriate neighborhood radius of the topographic measures.