详细信息
减少候选项集的数据流高效用项集挖掘算法
High utility itemsets mining algorithm of data stream with reducing candidate itemsets
文献类型:期刊文献
中文题名:减少候选项集的数据流高效用项集挖掘算法
英文题名:High utility itemsets mining algorithm of data stream with reducing candidate itemsets
作者:茹蓓[1];贺新征[2]
第一作者:茹蓓
机构:[1]新乡学院计算机与信息工程学院;[2]河南大学计算机与信息工程学院
第一机构:新乡学院计算机与信息工程学院
年份:2017
卷号:34
期号:11
起止页码:3379-3383
中文期刊名:计算机应用研究
外文期刊名:Application Research of Computers
收录:CSTPCD;;北大核心:【北大核心2014】;CSCD:【CSCD_E2017_2018】;
基金:河南省科技厅软科学研究计划资助项目(152400410345);河南省科技厅科技攻关资助项目(172102210445);河南省教育厅资助项目(15A520093)
语种:中文
中文关键词:大数据;数据流;高效用项集;模式挖掘;模式增长;候选模式
外文关键词:big data; data stream; high utility itemsets; pattern mining; pattern growth; candidate pattern
摘要:大数据环境下高效用项集挖掘算法中过多的候选项集极大地降低了算法的时空效率,为此提出了一种减少候选项集的数据流高效用项集挖掘算法。通过数据流中当前窗口的一次扫描建立一个全局树,并降低全局树中头表入口与节点的冗余效用值。基于全局树生成候选模式,基于增长算法降低局部树的候选项集效用,从候选模式中选出高效用模式。基于真实数据流的实验结果表明,算法的时空效率与内存占用比均优于其他数据流的高效用模式挖掘算法。
In the big data stream scenario, high utility pattern mining algorithm generated a lot of candidate itemsets and reduced the efficiency of time and space of algorithm. This paper proposed a high utility itemsets mining algorithm of data stream with reducing candidate itemsets to resolve that problem. Firstly, it constructed a global tree through a single scan of the current window in a data stream, reduced redundancy utilities in both entries of a header table and nodes in the tree in this stage. Secondly, it generated candidate patterns from the constructed tree, reduced the redundancy utilities of local tree by growth algorithm. Lastly, it identified a set of high utility patterns from the candidate patterns. Realistic data streams based experimental results show that the proposed algorithm performs better in efficiency of time and space and memory usage index than the other high utility pattern mining algorithm of data streams.
参考文献:
正在载入数据...