摘要
为减少构建效用列表的数量和占用的内存,在时间和空间方面提高挖掘性能,提出增量闭合高效用挖掘算法(incremental closed high utility mining,ICHUM),从增量数据集中有效地挖掘闭合高效用项集。此算法提出一个增量分区效用列表结构,该结构仅通过一次数据库扫描即可构建和更新列表,更有效地处理增量数据。在构造此列表结构的过程中,算法还应用有效的融合修剪策略,从而减少无效列表的构建数量。在各种数据集上的试验结果表明,与对比算法相比,该算法减少了30%的运行时间和33%的内存消耗,具有一定的可扩展性。
In order to reduce the number of constructing utility lists and the memory occupied,and improve the mining performance in terms of time and space,an incremental closed high utility mining algorithm(ICHUM) was proposed to effectively mine closed high utility items from the incremental data sets.This algorithm proposed an incremental partition utility list structure that builded and updated the list with only one database scan,processing incremental data more efficiently.In the process of constructing the list structure,the algorithm also applied an efficient fusion pruning strategy,which reduced the number of invalid lists constructed.The experimental results on various datasets showed that the algorithm reduced the running time by 30% and the memory consumption by 33% compared with the comparison algorithms,and had certain scalability.
作者
张春砚
韩萌
孙蕊
杜诗语
申明尧
ZHANG Chunyan;HAN Meng;SUN Rui;DU Shiyu;SHEN Mingyao(School of Computer Science and Engineering,North Minzu University,Yinchuan 750021,Ningxia,China)
出处
《山东大学学报（工学版）》
CAS
CSCD
北大核心
2022年第4期118-130,共13页
Journal of Shandong University（Engineering Science）
基金
国家自然科学基金资助项目(62062004)
宁夏自然科学基金资助项目(2020AAC03216)
北方民族大学研究生创新项目资助项目(YCX20061)。
关键词
增量挖掘
闭合高效用模式
增量分区效用列表
效用
融合修剪策略
incremental mining
closed high utility pattern
incremental partition utility list
utility
fusion pruning strategy
