Title :
Fast evaluation of t-norms for fuzzy association rules mining
Author_Institution :
Inst. for Res. & Applic. of Fuzzy Modeling, Univ. of Ostrava, Ostrava, Czech Republic
Abstract :
The aim of this paper is to present a bitwise approach on evaluation of fuzzy t-norms. T-norms are functions that generalize the notion of conjunction, and as such play an important role in fuzzy association rule mining process. Efficient algorithms for batch evaluation of the most common t-norms is proposed that minimizes computation time as well as memory space requirements at the cost of user-adjustable loss of precision of the membership degrees.
Keywords :
data mining; fuzzy set theory; batch evaluation; bitwise approach; fuzzy association rule mining process; fuzzy t-norms; membership degrees; memory space requirements; user-adjustable precision loss; Arrays; Association rules; Computational intelligence; Computers; Fuzzy sets; Indexes; Random access memory;
Conference_Titel :
Computational Intelligence and Informatics (CINTI), 2013 IEEE 14th International Symposium on
Conference_Location :
Budapest
Print_ISBN :
978-1-4799-0194-4
DOI :
10.1109/CINTI.2013.6705242
