一种基于不确定数据流的频繁模式挖掘算法  

A Frequent Pattern Mining Algorithm Based on Uncertain Data Stream

作　　者：王菊 靳春杰 闫迪 WANG Ju;JIN Chun-jie;YAN Di(PAP Academy,Beijing 100020,China;Datong Base of Air Force,Datong 037000,China;Beijing Institute of Remote Sensing Information,Beijing 100089,China)

机构地区：[1]武警部队研究院,北京100020 [2]空军大同基地,山西大同037000 [3]北京市遥感信息研究所,北京100089

出　　处：《装甲兵学报》2022年第2期78-86,共9页Journal of Armored Forces

摘　　要：针对在不确定数据流上的频繁模式挖掘问题,设计了用于存储项可靠度的期望支持数加权(Weighted with Expected Support,WES)矩阵和只存储有事务分组信息和项支持数的分组支持数树(Expected Support tree with Batches Information,ESBI-tree),提出了一种基于不确定数据流的期望频繁模式挖掘(Expected Frequent Pattern Mining over Uncertain data Stream,EFPMUS)算法。在试验中,将EFPMUS算法与SUF-growth(Frequent items growth from Streams of Uncertain data)、DSUF-mine(algorithm to mine Frequent pattern based on probability Decay of Sliding window over Uncertain data Stream)、BSUF-mine(efficient algorithm for mine Frequent pattern Based on Sliding window over Uncertain data streams)算法在运行时间、占用内存、模式数量和可扩展性上的性能进行了比较和分析,表明该算法可高效地从不确定数据流中挖掘出期望频繁模式。To solve the problem of frequent pattern mining over uncertain data stream,Weighted with Expected Support(WES)matrix that stores item reliability and Expected Support tree with Batches Information(ESBI-tree)that only stores transaction batch information and item support numbers are designed.Then,an Expected Frequent Pattern Mining algorithm over Uncertain data Stream(EFPMUS)is proposed.In the experiment,the algorithms EFPMUS,SUF-growth(frequent items growth from Streams of Uncertain Data),DSUF-mine(algorithm to mining Frequent pattern based on probability Decy of over Uncertain data Streams sliding window),and BSUF-mine(efficient algorithm for mining Frequent pattern Based on Sliding window over Uncertain data streams)are compared and analyzed in terms of running time,memory occupancy,number of patterns,and extensibility.It is shown that the proposed algorithm can efficiently excavate the expected frequent patterns over uncertain data stream.

关 键 词：数据挖掘 不确定数据流 频繁模式 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]