摘要
Apriori算法是关联规则挖掘的经典算法,具有原理简洁、易编程实现等优点,得到广泛应用。针对该算法扫描数据库次数过多,产生大量冗余候选集的缺陷,在现有Apriori算法改进优化思想的基础上,结合矩阵、改进频繁模式树和计算候选集频数优化策略提出了一种改进的关联规则挖掘算法——MIFP-Apriori算法。实验表明,该算法能够将扫描数据库次数降低到一次,有效解决产生大量冗余候选集的缺陷,提高算法效率。
Apriori algorithm is a classic algorithm for association rule mining.It has the advantages of simple principle and easy programming,and is widely used.Aiming at the fact that the algorithm scans the database too many times and generates a large number of redundant candidate sets,based on the existing Apriori algorithm improved optimization idea,an improvement association rule mining algorithm-MIFP-Apriori algorithm,was proposed based with the combination of matrix,improved frequent pattern tree and calculation candidate set frequency optimization strategy.Experiments show that the algorithm can reduce the number of scan databases to one time,effectively solve the defects of generating a large number of redundant candidate sets and improve the efficiency of the algorithm.
作者
曾子贤
巩青歌
张俊
ZENG Zi-xian;GONG Qing-ge;ZHANG Jun(Postgraduate Brigade,Engineering University of People Armed Police,Xi'an 710086,China;College of Information Engineering ,Engineering University of People Armed Police,Xi'an 710086,China)
出处
《科学技术与工程》
北大核心
2019年第16期216-220,共5页
Science Technology and Engineering
基金
陕西省自然科学青年基金(2015JQ6224)资助
