期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：4
页码：6793
DOI：10.15680/IJIRCCE.2017.0504031
出版社：S&S Publications
摘要：The main objective of this research work is to find the frequent items and association rule generation byusing the Enhanced-Apriori and Enhanced-Eclat algorithms. In data mining, normally association rule generationprocess consists of two steps; first step is finding the frequent items based on the minimum support threshold which isassigned commonly to all the items and the second step is the association rule generation. This research work also usedthe same steps with small modification i.e. in the first step, instead of assigning common minimum support threshold,this work has assigned an individual minimum support threshold to each and every item in the database, from thisfrequent items are found and association rules are generated. Performance factors used are execution time, memoryspace, number of frequent items and number of rules generated. Different sizes of datasets and threshold are used forexperimentation. From the results, we observed that the Enhanced-Apriorialgorithm has produced good results thanEnhanced- Eclat algorithm.
关键词：Frequent item mining; Association Rule Mining; Enhanced Apriori; Enhanced Eclat.
