Mining Multiple Clustering Data for Knowledge Discovery

Quan, T. T., Hui, S. C. and Fong, A. (2003) Mining Multiple Clustering Data for Knowledge Discovery. In: 6th International Conference on Discovery Science, Sapporo, Japan, 17-19 Oct 2003, pp. 452-459. ISBN 9783540396444 (doi: 10.1007/978-3-540-39644-4_45)

Abstract

Clustering has been widely used for knowledge discovery. In this paper, we propose an effective approach known as Multi-Clustering to mine the data generated from different clustering methods for discovering relationships between clusters of data. In the proposed Multi-Clustering technique, it first generates combined vectors from the multiple clustering data. Then, the distances between the combined vectors are calculated using the Mahalanobis distance. The Agglomerative Hierarchical Clustering method is used to cluster the combined vectors. And finally, relationship vectors that can be used to identify the cluster relationships are generated. To illustrate the technique, we also discuss an application example that uses the proposed Multi-Clustering technique to mine the author clusters and document clusters for identifying the relationships on authors working on research areas. The performance of the proposed technique is also evaluated.

• Item Type: Conference Proceedings
• Additional Information: Lecture notes in computer science: 2843
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Fong, Dr Alvis Cheuk Min
• Authors: Quan, T. T., Hui, S. C., and Fong, A.
• College/School: College of Science and Engineering > School of Computing Science
• ISSN: 0302-9743
• ISBN: 9783540396444