Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Comparison of algorithms that select features for pattern classifiers
Autore:
Kudo, M; Sklansky, J;
Indirizzi:
Hokkaido Univ, Grad Sch Engn, Div Syst & Informat Engn, Sapporo, Hokkaido 0608628, Japan Hokkaido Univ Sapporo Hokkaido Japan 0608628 oro, Hokkaido 0608628, Japan Univ Calif Irvine, Dept Elect Engn, Irvine, CA 92697 USA Univ Calif Irvine Irvine CA USA 92697 pt Elect Engn, Irvine, CA 92697 USA Natl Sci Fdn, Japan US Cooperat Sci Program, Washington, DC 20550 USA NatlSci Fdn Washington DC USA 20550 ci Program, Washington, DC 20550 USA Japan Soc Promot Sci, Tokyo, Japan Japan Soc Promot Sci Tokyo JapanJapan Soc Promot Sci, Tokyo, Japan
Titolo Testata:
PATTERN RECOGNITION
fascicolo: 1, volume: 33, anno: 2000,
pagine: 25 - 41
SICI:
0031-3203(200001)33:1<25:COATSF>2.0.ZU;2-7
Fonte:
ISI
Lingua:
ENG
Soggetto:
FLOATING SEARCH METHODS;
Keywords:
feature selection; monotonicity; genetic algorithms; leave-one-out method; k-nearest-neighbor method;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
16
Recensione:
Indirizzi per estratti:
Indirizzo: Kudo, M Hokkaido Univ, Grad Sch Engn, Div Syst & Informat Engn, Kita 13,Nishi 8, Sapporo, Hokkaido 0608628, Japan Hokkaido Univ Kita 13,Nishi 8 Sapporo Hokkaido Japan 0608628 Japan
Citazione:
M. Kudo e J. Sklansky, "Comparison of algorithms that select features for pattern classifiers", PATT RECOG, 33(1), 2000, pp. 25-41

Abstract

A comparative study of algorithms for large-scale feature selection (wherethe number of features is over 50) is carried out. In the study, the goodness of a feature subset is measured by leave-one-out correct-classificationrate of a nearest-neighbor (1-NN) classifier and many practical problems are used. A unified way is given to compare algorithms having dissimilar objectives. Based on the results of many experiments, we give guidelines for the use of feature selection algorithms. Especially, it is shown that sequential floating search methods are suitable for small- and medium-scale problems and genetic algorithms are suitable for large-scale problems. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 05/04/20 alle ore 06:10:32