广东工业大学学报2017，Vol.34Issue(2)：86-91,6.DOI:10.12052/gdutxb.150120
IFAMR:一种基于MapReduce的高效频繁项挖掘算法
IFAMR: An Efficent Frequent Itemset Mining Algorithm Based on MapReduce
摘要
Abstract
Considering that single host in the existing parallel computing framework is not efficient in accelerating massive data mining frequent item, an improved efficient algorithm for mining frequent item IFAMR is proposed, combining the advantages of the MapReduce parallel computing model according to the basic principle of Apriori algorithm and based on the algorithm FAMR. This algorithm first uses AprioriTID algorithm to preprocess the raw data, deleting all the low-frequency 1-itemsets, and then calculate the length of each transaction set (L) and minimum support (N) to determine the maximum merger candidate Map sets of operations. IFAMR algorithm reduces the Map function to generate a low-frequency item set, and the algorithms are proved by experimental comparison to have greatly reduced memory footprint and effectively improved the efficiency of the mining process.关键词
频繁项集挖掘/MapReduce/FAMR/Apriori/HadoopKey words
FIM (frequent itemset mining)/MapReduce/FAMR (frequent itemset mining algorithm based on MapReduce)/Apriori/Hadoop分类
信息技术与安全科学引用本文复制引用
刘祥佳,程良伦..IFAMR:一种基于MapReduce的高效频繁项挖掘算法[J].广东工业大学学报,2017,34(2):86-91,6.基金项目
国家基金广东省联合基金重点项目(U2012A002D01) （U2012A002D01）
国家自然科学基金青年科学基金资助项目(61502110) （61502110）
