%0 Conference Proceedings
%T A New Clustering Algorithm Based on Regions of Influence with Self-Detection of the Best Number of Clusters
%+ Laboratoire Hubert Curien (LHC)
%+ Equipe de Recherche en Ingénierie des Connaissances (ERIC)
%A Muhlenbach, Fabrice
%A Lallich, Stéphane
%Z 6 pages
%< avec comité de lecture
%( Proceeding of the Ninth IEEE International Conference on Data Mining
%B The Ninth IEEE International Conference on Data Mining
%C Miami, Florida, United States
%Y IEEE Computer Science
%I Conference Publishing Service
%P 884-888
%8 2009-12-06
%D 2009
%K clustering
%K neighborhood graph
%Z Computer Science [cs]/Machine Learning [cs.LG]Conference papers
%X Clustering methods usually require to know the best number of clusters, or another parameter, e.g. a threshold, which is not ever easy to provide. This paper proposes a new graph-based clustering method called ``GBC'' which detects automatically the best number of clusters, without requiring any other parameter. In this method based on regions of influence, a graph is constructed and the edges of the graph having the higher values are cut according to a hierarchical divisive procedure. An index is calculated from the size average of the cut edges which self-detects the more appropriate number of clusters. The results of GBC for 3 quality indices (Dunn, Silhouette and Davies-Bouldin) are compared with those of K-Means, Ward's hierarchical clustering method and DBSCAN on 8 benchmarks. The experiments show the good performance of GBC in the case of well separated clusters, even if the data are unbalanced, non-convex or with presence of outliers, whatever the shape of the clusters.
%G English
%2 https://hal.science/hal-00446155/document
%2 https://hal.science/hal-00446155/file/article_FM_SL_ICDM_2009.pdf
%L hal-00446155
%U https://hal.science/hal-00446155
%~ UNIV-ST-ETIENNE
%~ IOGS
%~ CNRS
%~ UNIV-LYON2
%~ LAHC
%~ PARISTECH
%~ ERIC
%~ UDL
%~ ANR