一种基于SMP系统的并行关联规则挖掘算法  

A Parallel Algorithm for Mining Frequent Itemsets Based on SMP

作　　者：田卫东[1] 王丹阳[1] 胡学钢[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《广西师范大学学报（自然科学版）》2008年第3期147-150,共4页Journal of Guangxi Normal University:Natural Science Edition

基　　金：教育部新世纪优秀人才计划资助项目(NECT-04-0562);安徽省自然科学基金资助项目(050420207)

摘　　要：从大规模数据库中挖掘关联规则是数据挖掘研究的一个重要问题。基于内存共享的对称多处理器系统SMP是目前广泛应用的并行计算系统,在关联规则串行挖掘算法Apriori的基础上,针对SMP系统设计一种基于Hash树的并行算法。理论分析和实验表明算法是有效的,具有良好的加速比。Mining association rules from large databases is an important problem in data mining. Symmetric Multi-Processor systems based on memory-sharing have already been the widely used parallel computing system nowadays. In this paper,on the basis of the research of the apriori algorithm,which is the classic algorithm for mining association rules,a parallel algorithm which can be running on SMP machine was proposed. Through the performance analysis and experiment ,it can be easily concluded that this parallel algorithm works well and has speedup performance.

关 键 词：数据挖掘 关联规则 并行算法 对称多处理器 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]