一种改进的AprioriTid算法

针对经典Apriori算法多次扫描数据库产生I/O负载影响运行效率等问题,在对Apriori算法的原理及其相关改进算法研究的基础上,提出了一种基于压缩集的改进Apriori算法,即Apriori Tid_M算法.通过有效的裁剪方法减少无效项集的产生,减少候选项集的数量,从而提高算法的效率.仿真实验表明,在支持度相同但数据量不同,以及数据量相同但支持度不同这两种条件下,Apriori Tid_M算法在性能上和运算时间上都比Apriori算法有很大程度的改善.

An improved AprioriTid algorithm

In order to solve the problem that the I/O load generated in the repeated scanning database for the classic Apriori algorithm will affect the running efficiency, an improved AprioriTid algorithm based on the compression set, namely the AprioriTid_M algorithm, was proposed on the basis of the research on the principle of Apriori algorithm and its related improved algorithms. Through the effective pruning methods, the generation of invalid item sets was reduced, and the number of candidate item sets was decreased. Therefore, the efficiency of the algorithm was improved. The results of simulation experiments show that under such conditions as the same support degree but different data amount or the same data amount but different support degree, the performance and running time of AprioriTid_M algorithm get greatly improved compared with those of Apriori algorithm.