Title :
FROCH: a fuzzy expert system with easy maintenance
Author :
Shiraz, G.M. ; Compton, P. ; Martínez-Béjar, R.
Author_Institution :
Dept. of Artificial Intelligence, New South Wales Univ., Kensington, NSW, Australia
Abstract :
Maintenance is a problem with all knowledge based systems, including fuzzy rule based systems. Although the use of fuzzy concepts partially reduces the maintenance problems, it introduces other problems in tuning the numbers used by the system. Ripple Down Rules (RDR) largely overcomes the maintenance problems for conventional crisp systems. The aim of this work was to apply the RDR approach to fuzzy rules to facilitate the maintenance and tuning of the numbers involved. On the other hand, the use of fuzzy concepts in the RDR system would allow the more natural expression of concepts, which is the main advantage of a fuzzy approach. The paper presents a theoretical foundation for combining RDR and fuzzy concepts
Keywords :
expert systems; fuzzy set theory; inference mechanisms; software maintenance; uncertainty handling; FROCH; RDR approach; Ripple Down Rules; easy maintenance; fuzzy concepts; fuzzy expert system; fuzzy rule based systems; fuzzy rules; knowledge based systems; maintenance problems; natural expression; theoretical foundation; Artificial intelligence; Computer science; Councils; Expert systems; Fuzzy systems; Hybrid intelligent systems; Knowledge acquisition; Knowledge based systems; Knowledge engineering; Maintenance engineering;
Conference_Titel :
Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4778-1
DOI :
10.1109/ICSMC.1998.724966
