A Robust Approach for Multivariate Binary Vectors Clustering and Feature Selection

Mohamed Al Mashrgy 1 Nizar Bouguila 1 Khalid Daoudi 2
1 CIISE - Concordia Institute for Information Systems Engineering
2 GeoStat - Geometry and Statistics in acquisition data
Inria Bordeaux - Sud-Ouest
Abstract : Given a set of binary vectors drawn from a ¯nite multiple Bernoulli mixture model, an important problem is to determine which vectors are outliers and which features are relevant. The goal of this paper is to propose a model for binary vectors clustering that accommo- dates outliers and allows simultaneously the incorporation of a feature selection methodology into the clustering process. We derive an EM al- gorithm to ¯t the proposed model. Through simulation studies and a set of experiments involving handwritten digit recognition and visual scenes categorization, we demonstrate the usefulness and e®ectiveness of our method.
Type de document :
Communication dans un congrès
International Conference on Neural Information Processing (ICONIP), Nov 2011, Shanghai, China. 2011
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-00647989
Contributeur : Khalid Daoudi <>
Soumis le : dimanche 4 décembre 2011 - 16:21:12
Dernière modification le : mercredi 29 novembre 2017 - 15:10:59
Document(s) archivé(s) le : lundi 5 mars 2012 - 02:20:43

Fichier

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

Identifiants

  • HAL Id : hal-00647989, version 1

Collections

INRIA

Citation

Mohamed Al Mashrgy, Nizar Bouguila, Khalid Daoudi. A Robust Approach for Multivariate Binary Vectors Clustering and Feature Selection. International Conference on Neural Information Processing (ICONIP), Nov 2011, Shanghai, China. 2011. 〈hal-00647989〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

614

Téléchargements de fichiers

821

Contact


archive-ouverte@inria.fr