ISSN:
1468-0394
Source:
Blackwell Publishing Journal Backfiles 1879-2005
Topics:
Computer Science
Notes:
Abstract: Much of the information resident in the knowledge base of a typical expert system is imprecise, incomplete or not totally reliable. The special features of a novel expert system shell based on fuzzy logic and numbers are presented. This rule-based system can deal with exact, inexact (fuzzy) and combined reasoning as well as uncertainty represented by fuzzy numbers. Natural language interface is built in naturally using fuzzy logic representation. Several application areas, namely, classification, risk analysis and information retrieval, are discussed with four appropriate sample expert systems actually built using this shell. Through these expert systems, the additional power and advantages over traditional expert systems are illustrated. It has been demonstrated that the introduction of fuzzy concepts into expert systesms is not feasible but highly desirable.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1111/j.1468-0394.1989.tb00070.x
Permalink