针对用户行为轨迹数据挖掘PrefixSpan算法构造投影数据库过程中重复扫描而造成时空开销过大的问题,提出一种改进的序列模式挖掘算法TDM-PrefixSpan(trajectory data mining based on prefixSpan algorithm)。依据时间序列分布特征,采用...针对用户行为轨迹数据挖掘PrefixSpan算法构造投影数据库过程中重复扫描而造成时空开销过大的问题,提出一种改进的序列模式挖掘算法TDM-PrefixSpan(trajectory data mining based on prefixSpan algorithm)。依据时间序列分布特征,采用具有轨迹数据预处理的SMM(statistical mobility model)算法,通过分段合并和自适应调整方法去除异常数据,解决轨迹数据存在大量pingpong效应的问题。采用频繁项集逆序挖掘序列模式,通过已挖掘序列模式集迭代去除冗余项集得到待挖掘序列模式集,缩短扫描候选数据库时间。数据集测试结果表明:SMM算法预处理后,原始数据库数据规模减小;通过对比可知,TDM-PrefixSpan算法能够有效降低时间复杂度,提升挖掘效率。展开更多
In order to reduce the computational and spatial complexity in rerunning algorithm of sequential patterns query, this paper proposes sequential patterns based and projection database based algorithm for fast interacti...In order to reduce the computational and spatial complexity in rerunning algorithm of sequential patterns query, this paper proposes sequential patterns based and projection database based algorithm for fast interactive sequential patterns mining algorithm （FISP）, in which the number of frequent items of the projection databases constructed by the correct mining which based on the previously mined sequences has been reduced. Furthermore, the algorithm＇s iterative running times are reduced greatly by using global-threshold. The results of experiments testify that FISP outperforms PrefixSpan in interactive mining展开更多
文摘针对用户行为轨迹数据挖掘PrefixSpan算法构造投影数据库过程中重复扫描而造成时空开销过大的问题,提出一种改进的序列模式挖掘算法TDM-PrefixSpan(trajectory data mining based on prefixSpan algorithm)。依据时间序列分布特征,采用具有轨迹数据预处理的SMM(statistical mobility model)算法,通过分段合并和自适应调整方法去除异常数据,解决轨迹数据存在大量pingpong效应的问题。采用频繁项集逆序挖掘序列模式,通过已挖掘序列模式集迭代去除冗余项集得到待挖掘序列模式集,缩短扫描候选数据库时间。数据集测试结果表明:SMM算法预处理后,原始数据库数据规模减小;通过对比可知,TDM-PrefixSpan算法能够有效降低时间复杂度,提升挖掘效率。
基金国家自然科学基金(the National Natural Science Foundation of Chinaunder Grant No.60373069)江苏省高校自然科学基金(the Col-lege Natural Science Foundation of Jiangsu Province of Chinaunder Grant No.05KJB520017)。
基金Supported by the National Natural Science Funda-tion of China (70371015) andthe Natural Science Foundation of Jian-gsu Province (BK2004058)
文摘In order to reduce the computational and spatial complexity in rerunning algorithm of sequential patterns query, this paper proposes sequential patterns based and projection database based algorithm for fast interactive sequential patterns mining algorithm （FISP）, in which the number of frequent items of the projection databases constructed by the correct mining which based on the previously mined sequences has been reduced. Furthermore, the algorithm＇s iterative running times are reduced greatly by using global-threshold. The results of experiments testify that FISP outperforms PrefixSpan in interactive mining
