Yahya Slimani ; Mohamed Amir Essegir ; Mouhamadou Lamine Samb ; Fodé Camara ; Samba Ndiaye - Approche de sélection d’attributs pour la classification basée sur l’algorithme RFE-SVM

arima:1965 - Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, August 18, 2014, Volume 17 - 2014 - Special issue CARI'12 - https://doi.org/10.46298/arima.1965
Approche de sélection d’attributs pour la classification basée sur l’algorithme RFE-SVMArticle

Authors: Yahya Slimani 1; Mohamed Amir Essegir 2; Mouhamadou Lamine Samb 3; Fodé Camara 3; Samba Ndiaye 3

  • 1 Ecole Supérieure de Technologie et d'Informatique [Tunis-Carthage]
  • 2 Laboratoire de Génie Informatique et d'Automatique de l'Artois
  • 3 département Mathématiques Informatique

The feature selection for classification is a very active research field in data mining and optimization. Its combinatorial nature requires the development of specific techniques (such as filters, wrappers, genetic algorithms, and so on) or hybrid approaches combining several optimization methods. In this context, the support vector machine recursive feature elimination (SVM-RFE), is distinguished as one of the most effective methods. However, the RFE-SVM algorithm is a greedy method that only hopes to find the best possible combination for classification. To overcome this limitation, we propose an alternative approach with the aim to combine the RFE-SVM algorithm with local search operators based on operational research and artificial intelligence.

Volume: Volume 17 - 2014 - Special issue CARI'12
Published on: August 18, 2014
Submitted on: January 30, 2014
Keywords: Data mining, Classification, Supervised classification, Feature selection, Support Vector Machines, Recursive Feature Elimination (RFE), Local search,[INFO] Computer Science [cs],[MATH] Mathematics [math]

Consultation statistics

This page has been seen 439 times.
This article's PDF has been downloaded 946 times.