Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Evolving granules for classification for discovering difference in the usage of words
Autore:
Yoshida, T; Kondo, T; Nishida, S;
Indirizzi:
Osaka Univ, Dept Syst & Human Sci, Grad Sch Engn Sci, Osaka 5608531, JapanOsaka Univ Osaka Japan 5608531 , Grad Sch Engn Sci, Osaka 5608531, Japan
Titolo Testata:
COMPUTATIONAL INTELLIGENCE
fascicolo: 3, volume: 17, anno: 2001,
pagine: 580 - 592
SICI:
0824-7935(200108)17:3<580:EGFCFD>2.0.ZU;2-4
Fonte:
ISI
Lingua:
ENG
Keywords:
usage of words; classification; decision tree; evolutionary approach; genetic algorithm; diversity;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
10
Recensione:
Indirizzi per estratti:
Indirizzo: Yoshida, T Osaka Univ, Dept Syst & Human Sci, Grad Sch Engn Sci, 1-3 Machikaneyama Cho, Osaka 5608531, Japan Osaka Univ 1-3 Machikaneyama Cho Osaka Japan 5608531 31, Japan
Citazione:
T. Yoshida et al., "Evolving granules for classification for discovering difference in the usage of words", COMPUT INTE, 17(3), 2001, pp. 580-592

Abstract

This paper proposes an evolutionary approach for discovering difference inthe usage of words to facilitate collaboration among people. In general, different people seem to have different ways of conception and thus can havedifferent concepts even on the same thing. When people try to communicate their concepts with words, such difference in the meaning and usage can lead to misunderstanding in communication, which can hinder their collaboration. In our approach each granule of knowledge in classification from users is structured into a decision tree so that difference in the usage of words can be discovered as difference in the structure of decision trees. By treating each granule of classification knowledge (i.e., decision tree) as an individual in Genetic Algorithm (GA), evolution is carried out with respect to both classification efficiency of each individual and diversity as a population so that the granule for classification is gradually evolved with diverse structure. Experiments were carried out on motor diagnosis cases withartificially encoded difference in the usage of words and the result showsthe effectiveness of the proposed evolutionary approach.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 04/07/20 alle ore 18:21:43