关键词: 时间序列, shapelets, 分类, 类可分离性

Abstract: Time series shapelets are small subsequences that describe the local property of time series and maximally differentiate classes. Since the inception of shapelets, researchers have paid close attention to it. However, because of the high time complexity, this method can’t be used widely. A novel method（Non-Similar Discover of Shapelet, NSDS） is proposed to discover time series shapelets quickly. According to the character of non-similar of the shapelets, this paper sets a distance threshold to filter out similar subsequence in the candidate set. Then the class separability is used as the evaluation criterion of the filtered subsequence, and finally the best performance of multiple shapelets is selected. The experimental results show that the proposed method can greatly reduce the time of searching shapelets and maintain high classification accuracy. The method is extended to the multivariate time series, and the multiple classifiers are used to improve the classification accuracy.

Key words: time series, shapelets, classification, class separability