期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2012
卷号：9
期号：2
出版社：IJCSI Press
摘要：Association rule (AR) mining is a data mining task that attempts to discover interesting patterns or relationships between data in large databases. Genetic algorithm (GA) based on evolution principles has found its strong base in mining ARs. This paper analyzes the performance of GA in Mining ARs effectively based on the variations and modification in GA parameters. The recent works in the past seven years for mining association rules using genetic algorithm is considered for the analysis. Genetic algorithm has proved to generate more accurate results when compared to other formal methods available. The fitness function, crossover rate, and mutation rate parameters are proven to be the primary parameters involved in implementation of genetic algorithm. Variations and modifications introduced in primary GA parameters are found to have greater impact in increasing the accuracy of the system moderately. The speedup of the system is found to increase when the selection and fitness function are altered.
关键词：Association rule; Genetic Algorithm; GA parameters; Accuracy; Speedup
