DocumentCode :
1659126
Title :
Comparison of heuristic rule weight specification methods
Author :
Ishibuchi, Hisao ; Yamamoto, Takashi
Author_Institution :
Dept. of Ind. Eng., Osaka Prefecture Univ., Japan
Volume :
2
fYear :
2002
fDate :
6/24/1905 12:00:00 AM
Firstpage :
908
Lastpage :
913
Abstract :
We examine the performance of heuristic methods for rule weight specification in fuzzy systems for pattern classification problems. Each heuristic method is defined by the confidence measure used in the field of data mining for evaluating association rules. Simulation results show that a proposed heuristic method outperforms existing ones
Keywords :
data mining; formal specification; fuzzy logic; fuzzy systems; heuristic programming; pattern classification; software performance evaluation; association rule evaluation; confidence measure; data mining; fuzzy systems; heuristic rule weight specification methods; pattern classification problems; performance; simulation; Association rules; Computational modeling; Computer simulation; Data mining; Fuzzy sets; Fuzzy systems; Industrial engineering; Knowledge based systems; Pattern classification; Terminology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems, 2002. FUZZ-IEEE'02. Proceedings of the 2002 IEEE International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7280-8
Type :
conf
DOI :
10.1109/FUZZ.2002.1006625
Filename :
1006625
Link To Document :
بازگشت