A new topological clustering algorithm for interval data

PATTERN RECOGNITION

卷:46

Article

Cabanes, Guenael¹  Bennani, Younes¹  Destenay, Renaud^2,3  Hardy, Andre^2,3 

[1] Univ Paris 13, CNRS, UMR 7030, LIPN, F-93430 Villetaneuse, France

[2] Univ Namur FUNDP, Namur Ctr Complex Syst naXys, B-5000 Namur, Belgium

[3] Univ Namur FUNDP, Dept Math, B-5000 Namur, Belgium

关键词: Interval data;    Clustering;    Self-organizing map;   

DOI  :  10.1016/j.patcog.2013.03.023

来源: Elsevier

【 摘 要 】

Clustering is a very powerful tool for automatic detection of relevant sub-groups in unlabeled data sets. In this paper we focus on interval data: i.e., where the objects are defined as hyper-rectangles. We propose here a new clustering algorithm for interval data, based on the learning of a Self-Organizing Map. The major advantage of our approach is that the number of clusters to find is determined automatically; no a priori hypothesis for the number of clusters is required. Experimental results confirm the effectiveness of the proposed algorithm when applied to interval data. (C) 2013 Elsevier Ltd. All rights reserved.

【 授权许可】

Free