Computational Efficiency of Parallel Distributed Genetic Fuzzy Rule Selection for Large Data Sets

Yusuke Nojima, Hisao Ishibuchi.

Genetic fuzzy rule selection is a two-phase classification rule mining method. First a large number of candidate fuzzy rules are generated by an association rule mining technique. Then only a small number of generated rules are selected by a genetic algorithm. We have already proposed an idea of parallel distributed implementation of genetic fuzzy rule selection. In this paper, we examine its computational efficiency for large data sets through computational experiments using a cluster system.

PDF full paper