关联规则中Apriori算法的研究与改进
- 文章编号:
- 2096-1618(2016)增-0011-03
- 摘要:
- Apriori算法是挖掘关联规则中频繁项集的算法,其算法思想就是利用上一步生成的候选项集挖掘频繁项集,该算法在网络安全、电商等领域都有应用。Apriori算法虽然是应用非常广泛的数据挖掘算法,但是还存在一些缺陷,比如频繁扫面事务数据库和产生不必要的候选项集。通过分析Apriori算法的执行步骤,找出算法中的不足,提出两种改进算法:缩减事务数据库和压缩事务数据库映射的矩阵。通过实验比较两种改进算法和经典Apriori算法,分析结果,可以看出改进的两种算法较经典算法有较高的效率提高。
参考文献/References:
[1] Peng Gong,Chi Yang; Hui Li.The application of improved association rules data mining algorithm Apriori in CRM[J].2ndInternational Conference on Pervasive Computing and Applications.2007:52-66.
[2] Lu Lina,Chen Yaping,Wei Hengyi.Research on the algorithm Apriori of mining association rules.Mini-Micro System,2002,21(9):940-943.
[3] Michael O AKinde.Efficient OLAP Query Processing in Distributed Data Warehouses[J].Lecture Notes in Computer Science,2004,(3):132-141.
[4] Tomoaki Imamura, Shinya Matsumoto,Yoshiyuki Kanagawa.A technique for identifying three diagnostic findings using association analysis[J].Medical and Biological Engineering and Computing.2007:51-59.
[5] Kleinberg J,Papadimitriou C,Raghavan P.Segmentation Problems[A].Proceedings of the 30th Annual Symposium on the Theory of Computing[C].New York:ACM Press,1998.
[6] M Nyanchama,S L Osborn.The role graph model and conflict of interest[J].ACMTISSEC,1999,2(1):3-33.
[7] LiX R,JilkovV P.A survey of maneuvering target tracking-part III:Measurement models[C]//Proceedings of the Confer-ence on Signal and Data Processing of Small Targets,CA,2001,4473(7/8):423-446.
[8] 吴斌,肖刚,陆佳炜.基于关联规则领域的Apriori算法的优化研究[J].计算机工程与科学,2009,31(6):116-118.
[9] J Ming,SyanChen.“DataMining:AnOverview fromaDatabasePersPeetive[J].IEEE Transaetions on Knowledge and Data Engineering,1996,8(6):866-883.
[10] Agrawal R,Srikant R. Fast algorithms for mining associa-tion rules in large database[C]//Proc of the 20th InternationalConference on Very Large Databases,1994.
备注/Memo
收稿日期:2016-02-28