Knowledge acquisition for probabilistic expert systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The probabilstic formalism has been used in creating the REFEREE system, a belief-network-based expert system designed to aid readers in determining the credibility of a randomized clinical trial. The effect the formalism had on the process of knowledge acquisition based on this experience is explored. Although the system is still in development, several of those effects are reported. Specifically, the need to make operational definitions of concepts deemed important to the expert forced the organization of a domain that was formulated initially for a rule-based system. Categorizing probability distributions as being logical, probabilistic, or prototypical helped to decrease the number of probability assessments. On the other hand, the lack of an intermediate prototype may have prolonged development, and computational limitations forced occasional compromises.

Original languageEnglish (US)
Title of host publicationProceedings - Annual Symposium on Computer Applications in Medical Care
EditorsRobert A. Greenes
PublisherPubl by IEEE
Pages73-77
Number of pages5
ISBN (Print)0818608811
StatePublished - Nov 1988
Externally publishedYes
EventProceedings - Twelfth Annual Symposium on Computer Applications in Medical Care - Washington, DC, USA
Duration: Nov 6 1988Nov 9 1988

Other

OtherProceedings - Twelfth Annual Symposium on Computer Applications in Medical Care
CityWashington, DC, USA
Period11/6/8811/9/88

Fingerprint

Knowledge acquisition
Knowledge based systems
Bayesian networks
Expert systems
Probability distributions

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Lehmann, H. P. (1988). Knowledge acquisition for probabilistic expert systems. In R. A. Greenes (Ed.), Proceedings - Annual Symposium on Computer Applications in Medical Care (pp. 73-77). Publ by IEEE.

Knowledge acquisition for probabilistic expert systems. / Lehmann, Harold P.

Proceedings - Annual Symposium on Computer Applications in Medical Care. ed. / Robert A. Greenes. Publ by IEEE, 1988. p. 73-77.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lehmann, HP 1988, Knowledge acquisition for probabilistic expert systems. in RA Greenes (ed.), Proceedings - Annual Symposium on Computer Applications in Medical Care. Publ by IEEE, pp. 73-77, Proceedings - Twelfth Annual Symposium on Computer Applications in Medical Care, Washington, DC, USA, 11/6/88.
Lehmann HP. Knowledge acquisition for probabilistic expert systems. In Greenes RA, editor, Proceedings - Annual Symposium on Computer Applications in Medical Care. Publ by IEEE. 1988. p. 73-77
Lehmann, Harold P. / Knowledge acquisition for probabilistic expert systems. Proceedings - Annual Symposium on Computer Applications in Medical Care. editor / Robert A. Greenes. Publ by IEEE, 1988. pp. 73-77
@inproceedings{bc23621559cf4dc585650e0e924d18eb,
title = "Knowledge acquisition for probabilistic expert systems",
abstract = "The probabilstic formalism has been used in creating the REFEREE system, a belief-network-based expert system designed to aid readers in determining the credibility of a randomized clinical trial. The effect the formalism had on the process of knowledge acquisition based on this experience is explored. Although the system is still in development, several of those effects are reported. Specifically, the need to make operational definitions of concepts deemed important to the expert forced the organization of a domain that was formulated initially for a rule-based system. Categorizing probability distributions as being logical, probabilistic, or prototypical helped to decrease the number of probability assessments. On the other hand, the lack of an intermediate prototype may have prolonged development, and computational limitations forced occasional compromises.",
author = "Lehmann, {Harold P}",
year = "1988",
month = "11",
language = "English (US)",
isbn = "0818608811",
pages = "73--77",
editor = "Greenes, {Robert A.}",
booktitle = "Proceedings - Annual Symposium on Computer Applications in Medical Care",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Knowledge acquisition for probabilistic expert systems

AU - Lehmann, Harold P

PY - 1988/11

Y1 - 1988/11

N2 - The probabilstic formalism has been used in creating the REFEREE system, a belief-network-based expert system designed to aid readers in determining the credibility of a randomized clinical trial. The effect the formalism had on the process of knowledge acquisition based on this experience is explored. Although the system is still in development, several of those effects are reported. Specifically, the need to make operational definitions of concepts deemed important to the expert forced the organization of a domain that was formulated initially for a rule-based system. Categorizing probability distributions as being logical, probabilistic, or prototypical helped to decrease the number of probability assessments. On the other hand, the lack of an intermediate prototype may have prolonged development, and computational limitations forced occasional compromises.

AB - The probabilstic formalism has been used in creating the REFEREE system, a belief-network-based expert system designed to aid readers in determining the credibility of a randomized clinical trial. The effect the formalism had on the process of knowledge acquisition based on this experience is explored. Although the system is still in development, several of those effects are reported. Specifically, the need to make operational definitions of concepts deemed important to the expert forced the organization of a domain that was formulated initially for a rule-based system. Categorizing probability distributions as being logical, probabilistic, or prototypical helped to decrease the number of probability assessments. On the other hand, the lack of an intermediate prototype may have prolonged development, and computational limitations forced occasional compromises.

UR - http://www.scopus.com/inward/record.url?scp=0024112322&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024112322&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024112322

SN - 0818608811

SP - 73

EP - 77

BT - Proceedings - Annual Symposium on Computer Applications in Medical Care

A2 - Greenes, Robert A.

PB - Publ by IEEE

ER -