【摘要】 提出一种基于静态IS-树的频繁模式挖掘有效算法IS-mine,并与经典的Apriori算法和FP-growth算法进行了实验比较。算法直接构造频繁项集,不进行Apriori算法采用的代价较高的候选集产生与测试操作。算法采用深度优先,模式增长的策略,挖掘任务只在一棵静态的IS-树上进行,避免了FP-growth算法所采用的代价较高的动态树的构建。针对不同特征数据集算法采取不同的过滤技术来缩小搜索空间。实验与理论分析表明,对于稠密和稀疏数据两类数据集,算法都具有较好的时空效率。更多还原

【Abstract】 In this paper, an algorithm is presented for mining frequent patterns based on a static IS- tree. The algorithm builds frequent patterns directly, instead of high-cost candidate sets generation- and-test method used by Apriori. It generates frequent patterns by depth first and pattern growth approach, and works on a static IS-tree, rather than a costly dynamic tree adopted by FP-growth. In order to reduce search space, it uses different filter technologies according to different characteristics of datasets. Our performance study and theory analysis show that it is efficient in both dense datasets and sparse datasets.更多还原