Feature Selection for Classification Using an Ant System Approach - Distributed, Parallel and Biologically Inspired Systems Access content directly
Conference Papers Year : 2010

Feature Selection for Classification Using an Ant System Approach

Abstract

Many applications such as pattern recognition and data mining require selecting a subset of the input features in order to represent the whole set of features. The aim of feature selection is to remove irrelevant, redundant or noisy features while keeping the most informative ones. In this paper, an ant system approach for solving feature selection for classification is presented. The results we got are promising in terms of the accuracy of the classifier and the number of selected features in all the used datasets.
Fichier principal
Vignette du fichier
final_02.pdf (62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01054496 , version 1 (07-08-2014)

Licence

Attribution

Identifiers

Cite

Nadia Abd-Alsabour. Feature Selection for Classification Using an Ant System Approach. 7th IFIP TC 10 Working Conference on Distributed, Parallel and Biologically Inspired Systems (DIPES) / 3rd IFIP TC 10 International Conference on Biologically-Inspired Collaborative Computing (BICC) / Held as Part of World Computer Congress (WCC) , Sep 2010, Brisbane, Australia. pp.233-241, ⟨10.1007/978-3-642-15234-4_23⟩. ⟨hal-01054496⟩
139 View
534 Download

Altmetric

Share

Gmail Facebook X LinkedIn More