摘要
通过对Apriori算法挖掘过程的深入分析,提出一种改进的关联规则挖掘算法——基于事务相似矩阵的关联规则挖掘算法(ARBSM):在压缩事务布尔矩阵的基础上构建一个事务相似矩阵,直接查找高阶K-项频繁集,有效解决了Apriori算法逐层搜索的迭代产生频繁项集的瓶颈问题。测试结果表明,ARBSM算法可以高效地挖掘潜在的强关联规则。
With in-depth analysis of mining association rules, an improved association rule mining algorithm: Association Rule Mining Algorithm Based on Similarity Matrix of Transations (ARBSM), is proposed. Innovation of the algorithm creates a similarity matrix of transactions based on reducing matrix of transactions. The algorithm directly finding the high level frequent itemsets effectively resolves the bottleneck of Apriori algorithm. The experiment shows that ARBSM algorithm can effectively find out the strong potential association rules.
出处
《桂林工学院学报》
北大核心
2008年第4期568-571,共4页
Journal of Guilin University of Technology
基金
广西自然科学基金资助项目(桂科自0832264)
广西区教育厅科研项目(200708MS165)