时间序列数据挖掘的相似性度量综述  

Survey on similarity measurement of time series data mining

作　　者：陈海燕[1,2] 刘晨晖[1] 孙博[1] 

机构地区：[1]南京航空航天大学计算机科学与技术学院,南京210016 [2]南京航空航天大学软件新技术与产业化协同创新中心,南京210016

出　　处：《控制与决策》2017年第1期1-11,共11页Control and Decision

基　　金：国家自然科学基金项目(61501229);中央高校基本科研业务费专项资金项目(NS2015091;NJ20160013)

摘　　要：在时间序列数据挖掘中,时间序列相似性是一个重要的概念.对于诸多算法而言,能否与一种合适的相似性度量方法结合应用,对其挖掘性能有着关键影响.然而,至今仍没有统一的度量相似性的方法.对此,首先综述了常用的相似性度量方法,分析了各自的优点与不足;其次,讨论了近年来出现的时序相似性的新解释及其度量方法;再次,探讨了相似性度量在时序挖掘任务中的应用以及与挖掘精度的关系;最后给出了关于时序相似性度量进一步的研究方向.Similarity measure is an important concept in time series data mining. For many data mining algorithms,whether it can be used in combination with a suitable time series similarity measure method has a key influence on mining performance. However, there is no uniform definition and measure of similarity. Therefore, we first introduce the most popular similarity measures, and analyze the advantages and disadvantages of each measure. Then, the new interpretations of the time series similarity and the corresponding measures are discussed. Furthermore, we analyze the applications of similarity measures in clustering, classification and regression of time series data, and the relationship between similarity measure and mining precision. Finally, several directions for the future research are given.

关 键 词：时间序列数据挖掘 时间序列相似性 相似性度量 挖掘精度 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]