摘要
FP-growth算法是一个挖掘频繁模式的有效算法,但它在挖掘过程中需要产生大量的条件FP树,因此其时空效率不够理想。提出了DFP-mine算法,通过在改进的FP树上合并子树来挖掘频繁模式,并在挖掘过程中结合了自顶向下和自底向上的双向搜索策略。理论分析和实验表明本文提出的算法具有较好的时空效率。
FP-growth is an efficient algorithm for mining frequent patterns, however, it needs to generate numerous re-construction of intermediate FP-trees during the mining process, so the efficiency of FP-growth remains unsatisfactory. This paper proposes an algorithm DFP-mine for mining frequent patterns by merging sub-trees in an advanced FP-tree. A search strategy that integrating the top to down and down to top method is introduced. Theoretical analysis and experimental results show that the algorithms proposed in this paper have higher efficiency.
出处
《广西师范大学学报（自然科学版）》
CAS
北大核心
2007年第4期252-256,共5页
Journal of Guangxi Normal University:Natural Science Edition
基金
福建省自然科学基金资助项目(A0610014)
福州大学科技发展基金资助项目(2005-XQ-13
2006-XQ-22)
