一种有效的挖掘数据流近似频繁项算法  

An Efficient Algorithm for Mining Approximate Frequent Item over Data Streams

作　　者：王伟平[1] 李建中[1] 张冬冬[1] 郭龙江[1] 

机构地区：[1]哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨150001

出　　处：《软件学报》2007年第4期884-892,共9页Journal of Software

基　　金：SupportedbytheKeyProgramoftheNationalNaturalScienceFoundationofChinaunderGrantNo.60533110(国家自然科学基金重点项目);theNationalNaturalScienceFoundationofChinaunderGrantNo.60473075(国家自然科学基金);theKeyProgramofNaturalScienceFoundationofHeilongjiangProvinceofChinaunderGrantNo.zjg03-05(黑龙江省自然科学基金);theProgramforNewCenturyExcellentTalentsinUniversityofChinaunderGrantNo.NCET-05-0333(新世纪优秀人才支持计划)

摘　　要：数据流频繁项是指在数据流中出现频率超出指定阈值的数据项.查找数据流频繁项在网络故障监测、流数据分析以及流数据挖掘等多个领域有着广泛的应用.在数据流模型下,算法只能一遍扫描数据,并且可用的存储空间远远小于数据流的规模,因此,挖掘出所有准确的数据流频繁项通常是不可能的.提出一种新的挖掘数据流近似频繁项的算法.该算法的空间复杂性为O(ε^(-1)),每个数据项的平均处理时间为O(1),输出结果的频率误差界限为ε(1-s+ε)N,在目前已有的同类算法中均为最优.A frequent item of a data stream is a data point whose occurrence frequency is above a given threshold. Finding frequent item of data stream has wide applications in various fields, such as network traffic monitor, data stream OLAP and data stream mining, etc. In data stream model, the algorithm can only scan the data in one pass and the available memory space is very limited relative to the volume of a data stream, therefore it is usually unable to find all the accurate frequent items of a data stream. This paper proposes a novel algorithm to find e-approximate frequent items of a data stream, its space complexity is O（ε^-1） and the processing time for each item is O（1） in average. Moreover, the frequency error bound of the results returned by the proposed algorithm is ε（1-s＋ε）N. Among all the existed approaches, this method is the best.

关 键 词：数据流 数据挖掘 频繁项 ε-近似 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]