【摘要】 时间序列是现实生活中常见的数据形式之一。在时间序列中发现频繁模式是分析时间序列变化规律的一项重要任务。本文提出一种基于互关联后继树模型的时间序列频繁模式发现方法。该方法依据序列重要点进行分段,引入相对斜率值并结合领域知识将序列符号化,在此基础上提出一种互关联后继树的新型挖掘算法,实现了时序频繁模式的发现。理论与实验表明,该方法简单、直观、高效,具有实用价值。更多还原

【Abstract】 Time Series are an important type of data. Discovering frequent patterns from time scries is basic task to predicate the changing trend of time series. In many existing methods in the literature, the mined patterns are described in shape, which is difficult to understand and use. Secondly these methods are basically based on the Apriori algorithm, which has to generate many pattern candidates so that the mining effciency is degraded. In this paper , a novel method is proposed to discovery frequent pattern from time series . It first segments time series based on,a series of perceptually important points , and then time series are converted into meaningful symbols sequences in terms of domain knowledge and the relative scope of each linear segment . After that , we designed a new data model, called Sequence Relevant Successive Trees (SRST), to find frequent patterns from multiple time series. Compared with the previous methods, the method is simpler and more flexible, efficient and useful.更多还原