【摘要】 从时序数据库中挖掘周期模式是重要的数据任务 ,而部分周期仅关心所有时间点中的一个子集的周期行为 ,它在现实世界中广泛存在 .本文提出了一个新颖的基于前缀图的挖掘频繁部分周期模式的算法 ,并通过实验证明了该算法在执行效率上比现有的挖掘频繁部分周期模式的算法有较大提高 .更多还原

【Abstract】 It is an essential task to mine frequent partial periodicity patterns from time series database.Partial periodicity,which associates only with periodic behavior of a subset at all time points,exists ubiquitously in the real world.In this paper,we proposed an efficient algorithm for mining frequent partial periodicity patterns based on a novel graph structure,and proved that this algorithm is more efficient than all the previous algorithms by experiment.更多还原