基于Apriori的快速剪枝和连接的新算法（英文）  

A New Quick Pruning and Connection Algorithm Based on Apriori

作　　者：李雷[1] 黄蓉[1] 

机构地区：[1]南京邮电大学自动化学院,江苏南京210000

出　　处：《计算机技术与发展》2014年第5期31-35,共5页Computer Technology and Development

基　　金：国家自然科学基金资助项目(61070234)

摘　　要：挖掘关联规则是目前数据挖掘领域热点研究话题之一。它的目的在于在数据库中挖掘有趣的关联规则。在关联规则分析及Apriori算法分析上,针对Apriori算法的瓶颈问题,许多有效的改进算法被提出。文中提出了QPCA算法。该算法利用矩阵分析的方法,仅需要扫描数据库一次,同时此算法优化了连接和剪枝操作,通过快速的剪枝和连接可以很快地获取最少的候选项集,避免了频繁项集之间的重复判断连接,因此大大提高了算法的效率。实验结果表明,该算法在挖掘时间上有很大提高。Mining of association rules is an important research topic in data mining field. Its purpose is to mine interesting associations in transaction database. For the analysis of association rules and Apriori algorithm principle,in view of the bottlenecks of Apriori algorithm, lots of improved algorithms are proposed. In this paper,put forward the QPCA. The algorithm uses the method of matrix analysis,only needs to scan the database once. At the same time,the algorithm optimizes the pruning and connection operation,which can quickly obtain less candidate itemsets by quick pruning and connection,avoiding duplication of judgment and connection between frequent itemsets. Thus it＆#39;s greatly improving the efficiency of the algorithm. The experimental results show that the algorithm has great improvement in mining speed.

关 键 词：关联规则 数据挖掘 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]