基于线程并行计算的Apriori算法

1.福州大学 数学与计算机科学学院,福建 福州 350108; 2.福州大学 至诚学院,福建 福州 350108

线程; 并行计算; Apriori算法

Apriori algorithm based on thread parallel computing
YIN Ai-ying1,2

(1.College of Mathematics and Computer Science,Fuzhou University,Fuzhou 350108,China; 2.Department of Computer Engineering,Zhicheng College of Fuzhou University,Fuzhou 350108,China)

thread; parallel computing; apriori algorithm

备注

针对数据挖掘中经典的Apriori算法在计算频繁项目集时需消耗大量的时间缺点,文中利用多线程并行计算的特点,提出了基于线程并行计算的Apriori算法,该算法是将统计候选项目个数的任务交给多线程来执行,从而达到减少Apriori算法的运行时间。通过实验数据分析,该算法对减少Apriori算法的运行时间有很大的提高。

Considering the Apriori data mining algorithm in the classic calculation of frequent itemsets requires a lot of time,using characteristics of multi-threaded parallel computing,thread is proposed based on the Apriori algorithm of parallel computing,this algorithm is to hand the task of statistics of the number of candidate item over to multi-thread to execute,so as to reduce the running time of the Apriori algorithm.Through the analysis of the experimental data,the algorithm has improved greatly to reduce the running time of the Apriori algorithm.