基于聚类的区间数时间序列的索引方法

在时间序列数据库中，大多数现有的相似性搜索方法都集中在如何提高算法的效率，而对于由不精确数据组成的时间序列如何进行相似性搜索，则研究比较少，不精确数据经常用区间数据来表示；通过识别区间数时间序列中的重要区间数，使得区间数时间序列的维数大幅度降低，该文针对由区间数组成的时间序列，提出了一种基于低分率聚类的索引方法。实验表明，该方法加快了区间数时间序列的查找过程，不会出现漏报现象。

Time Series of Intervals Index Based on Clustering

Most existing approoches of similarity search in time series databases focus on the efficiency of algorithms but seldom provide a means to handle imprecise data. The imprecise data are normally presented in the interval. By identifying the important interval values from the time series of intervals, the dimensionality of the time series of intervals can be greatly reduced. This paper proposes an indexing approach of time series of intervals, based on clustering the time series of intervals in low resolution. As demonstrated by the experiments, the proposed approach speeds up the time series of intervals query process while it also guarantees no false dismissals,