Premium
Approximate reasoning with IF‐THEN‐UNLESS rules in a medical expert system
Author(s) -
Hudson D. L.,
Cohen M. E.,
Anderson M. F.
Publication year - 1992
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/int.4550070109
Subject(s) - expert system , computer science , model based reasoning , artificial intelligence , legal expert system , machine learning , management science , knowledge representation and reasoning , engineering
Abstract The rule‐based approach to the development of expert systems has been utilized for the past two decades. Recently, this approach has met with renewed criticism because of the inability of the resulting systems to provide robust decision models which accurately represent real‐world situations. Two methodologies which prove useful in the adjustment of these systems to realistic situations are the use of techniques of approximate reasoning and the incorporation of rules of the type IF‐THEN‐UNLESS, which provide options commonly used by human decision makers. Unfortunately, neither of these techniques has been used extensively in practical diagnostic systems. In the work described here, a expert system which utilizes approximate reasoning techniques has been modified to accommodate IF‐THEN‐UNLESS rules. Some practical considerations are presented.