Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Multiclass linear dimension reduction by weighted pairwise Fisher criteria
Autore:
Loog, M; Duin, RPW; Haeb-Umbach, R;
Indirizzi:
Univ Utrecht, Med Ctr, Image Sci Inst, NL-3508 GA Utrecht, Netherlands Univ Utrecht Utrecht Netherlands NL-3508 GA 3508 GA Utrecht, Netherlands Delft Univ Technol, Dept Appl Phys, Pattern Recognit Grp, NL-2600 GA Delft, Netherlands Delft Univ Technol Delft Netherlands NL-2600 GA 00 GA Delft, Netherlands Philips Res Labs, D-52066 Aachen, Germany Philips Res Labs Aachen Germany D-52066 es Labs, D-52066 Aachen, Germany
Titolo Testata:
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
fascicolo: 7, volume: 23, anno: 2001,
pagine: 762 - 766
SICI:
0162-8828(200107)23:7<762:MLDRBW>2.0.ZU;2-J
Fonte:
ISI
Lingua:
ENG
Soggetto:
DISCRIMINANT-ANALYSIS;
Keywords:
linear dimension reduction; Fisher criterion; linear discriminant analysis; Bayes error; approximate pairwise accuracy criterion;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
14
Recensione:
Indirizzi per estratti:
Indirizzo: Loog, M Univ Utrecht, Med Ctr, Image Sci Inst, POB 85500, NL-3508 GA Utrecht, Netherlands Univ Utrecht POB 85500 Utrecht Netherlands NL-3508 GA Netherlands
Citazione:
M. Loog et al., "Multiclass linear dimension reduction by weighted pairwise Fisher criteria", IEEE PATT A, 23(7), 2001, pp. 762-766

Abstract

We derive a class of computationally inexpensive linear dimension reduction criteria by introducing a weighted variant of the well-known It-class Fisher criterion associated with linear discriminant analysis (LDA). It can beseen that LDA weights contributions of individual class pairs according tothe Euclidian distance of the respective class means. We generalize upon LDA by introducing a different weighting function.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 27/11/20 alle ore 13:10:42