一种时间序列相似匹配新算法

为提高时间序列相似匹配的精度和效率，提出一种基于小波包变换的时间序列相似匹配算法．首先利用小波包可对信号进行精细分析的特点，对时间序列进行维数约简，用变换后的低频系数和部分高频均值系数作为特征向量表示原始序列；然后用多维索引结构R树存储这些特征向量，将欧几里德距离作为相似尺度，在此基础上实现了范围查询和k近邻查询，对电力负荷时间序列数据的仿真实验结果表明了算法的有效性。

A novel similar matching algorithm for time series data

In order to improve the accuracy and efficiency of time series similar matching, a novel similar matching algorithm is proposed. It reduces the dimensionality of time series data with wavelet packet transformation. Then, multidimensional index structure such as R tree is built using the selected coefficients. Euclidean distance is used as similarity measurement. Range query and k nearest neighbor query algorithms are presented. Experimental results on electrical load time series data show the effectiveness of the algorithm.