A New Clustering Algorithm Based on Regions of Influence with Self-Detection of the Best Number of Clusters

Abstract : 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.
Type de document :
Communication dans un congrès
IEEE Computer Science. The Ninth IEEE International Conference on Data Mining, Dec 2009, Miami, Florida, United States. Conference Publishing Service, pp.884-888, 2009
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00446155
Contributeur : Fabrice Muhlenbach <>
Soumis le : mardi 12 janvier 2010 - 11:03:51
Dernière modification le : mercredi 31 octobre 2018 - 12:24:08
Document(s) archivé(s) le : jeudi 17 juin 2010 - 20:47:30

Fichier

article_FM_SL_ICDM_2009.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00446155, version 1

Collections

Citation

Fabrice Muhlenbach, Stéphane Lallich. A New Clustering Algorithm Based on Regions of Influence with Self-Detection of the Best Number of Clusters. IEEE Computer Science. The Ninth IEEE International Conference on Data Mining, Dec 2009, Miami, Florida, United States. Conference Publishing Service, pp.884-888, 2009. 〈hal-00446155〉

Partager

Métriques

Consultations de la notice

277

Téléchargements de fichiers

330