Knowledge elicitation and integration from multiple experts

Author

Hwang, Gwo-Jen

Author_Institution

Comput. Center, Nat. Chiao Tung Univ., Hsinchu, Taiwan

fYear

1992

fDate

28-30 May 1992

Firstpage

208

Lastpage

211

Abstract

The idea of this paper is based upon the belief that each person has his (or her) own habitual domain, in which he (or she) used to solve problems by his (or her) own way. If a person´s habitual domain can not cover the problem to be solved, he (or she) will feel diffident and uneasy, and incorrect decisions may be made. For an expert to solve a problem within his (or her) habitual domain, overconfidence and ignorance may sometimes lead to mistakes. To cope with these problems, a knowledge acquisition method for multiple experts, MERGE, is proposed. Some experimental results on a practical application have shown that MERGE is able to enrich the elicited knowledge and improve the performance of the constructed expert systems by integrating expertise from multiple experts

Keywords

expert systems; knowledge acquisition; MERGE; expert systems; habitual domain; knowledge acquisition; knowledge elicitation; knowledge integration; multiple experts; performance; Amplitude shift keying; Buildings; Expert systems; Filling; Knowledge acquisition; Knowledge based systems; Prototypes; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing and Information, 1992. Proceedings. ICCI '92., Fourth International Conference on

Conference_Location

Toronto, Ont.

Print_ISBN

0-8186-2812-X

Type

conf

DOI

10.1109/ICCI.1992.227672

Filename

227672