基于粒度计算的数据流最大频繁项集更新方法  

Update Method of Maximum Frequent Itemsets inData Stream Based on Granular Computing

作　　者：周翔 ZHOU Xiang(Department of computing and Information Science,Fuzhou Institute of Technology,Fuzhou 350506,Fujian,China)

机构地区：[1]福州理工学院计算与信息科学学院,福建福州350506

出　　处：《贵阳学院学报（自然科学版）》2021年第2期1-5,共5页Journal of Guiyang University：Natural Sciences

基　　金：2020年度福建省教育厅中青年教师科研项目“基于粒度计算的大数据集频繁项挖掘方法”(项目编号:JAT200910);2020年度福州理工学院校级科研基金项目“基于粒度计算的大数据集频繁项挖掘方法”(项目编号:FTKY015)。

摘　　要：为提高对数据流内信息挖掘的程度,本文提出一种基于粒度计算的数据流最大频繁项集更新方法。根据数据流存在的不确定性特点,以属性的取值建立对象粒,将对数据流最大频繁项集的挖掘转化为相同属性对象粒的计算,将过程计算分为两部分,即实时数据流信息挖掘和数据流信息分析,引入对象粒计算方法对实时挖掘结果进一步分析,得出最大频繁项集,对其进行更新。实验结果表明,在实验条件下,在相对稀疏和稠密的数据流环境中,所提方法运行时间相对于对比方法至多可提升30%,最少所占内存可低至对比方法的50%,且相同条件下,随最小支持度阈值变化,运行时间减小幅度均明显少于对比方法,表明实验方法具有一定参考价值。In order to improve the degree of information mining in data stream,this paper proposes a maximum frequent itemset updating method based on granular computing.Firstly,according to the uncertainty characteristics of data stream,the object granule is established based on the value of attributes,and the mining of the maximum frequent itemsets of data stream is transformed into the calculation of the same attribute object granule.The process calculation is divided into two parts,namely real-time data stream information mining and data stream information analysis.The object granule calculation method is introduced to further analyze the real-time mining results,and the maximum frequent itemsets are obtained The experimental results show that under the experimental conditions,compared with the comparison method,the running time of the proposed method can be improved by 30%at most,and the minimum memory can be as low as 50%of the comparison method in the relatively sparse and dense data stream environment.Moreover,under the same conditions,with the change of the minimum support threshold,the reduction of the running time is significantly less than that of the comparison method The results show that the proposed method has a certain reference value.

关 键 词：数据流 粒度计算 最大频繁项集 最小支持度阈值 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]