基于事件的时间序列相似性度量方法  

Time series similarity matching based on event

作　　者：吴学雁[1,2] 黄道平[1] 

机构地区：[1]华南理工大学自动化科学与工程学院,广州510640 [2]广东工业大学管理学院,广州510520

出　　处：《计算机应用》2010年第7期1944-1946,共3页journal of Computer Applications

基　　金：广东工业大学青年基金资助项目(092036)

摘　　要：为了更好地体现用户需求,提高时间序列相似性度量的准确度,提出了基于事件的时间序列相似性度量(SMBE)方法。首先将用户的需求定义为事件,构建了SMBE模型;然后,构建相应的相似性矩阵,并对相似性矩阵进行搜索得到最优路径的值作为序列之间的相似性度量;最后,提出了基于SMBE的聚类方法。实验表明,在参数设置合理的情况下,能获得接近0.90的聚类精度。SMBE方法通过对事件的定义引入用户需求,提高了时间序列相似性度量的准确性。In order to do the time-series similarity matching with the users＇ needs and improve the accuracy,the time-series similarity matching based on event（SMBE） was proposed.First,the users＇ needs were defined as the event and SMBE was constructed.Then,the corresponding similarity matrix was constituted and the optimal path value was searched as the similarity measurement.Finally,the clustering method based on SMBE was proposed.The experimental results show that the clustering based on SMBE can get the accuracy of 90% with the reasonable parameters.SMBE improves the accuracy of similarity measurement with the users＇ needs represented by the event.

关 键 词：时间序列 相似性度量 聚类 数据挖掘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]