基于2dSVD和高斯混合模型的多变量时间序列聚类

MULTI-VARIATE TIME SERIES CLUSTERING BASED ON TWO-DIMENSIONAL SINGULAR VALUE DECOMPOSITION AND GAUSSIAN MIXTURE MODEL

针对多变量时间序列(MTS)存在时间和变量两个维度,以及传统主成分分析(PCA)方法在MTS数据表示上的局限性,提出一种基于二维奇异值分解(2dSVD)和高斯混合模型(GMM)的MTS聚类算法。该文计算MTS的行-行和列-列协方差矩阵的特征向量,从时间和变量两个维度提取特征矩阵;用GMM从概率分布角度对特征矩阵进行聚类。数值实验结果表明,该方法对多变量时间序列具有更好的聚类效果。

Multi-variable time series(MTS)has two dimensions,time and variable,and traditional principal component analysis(PCA)is limited in MTS data representation.Therefore,a MTS clustering algorithm based on the two-dimensional singular value decomposition(2dSVD)and Gaussian mixture model(GMM)is proposed.We calculated the eigenvectors of the row-row and column-column covariance matrix of MTS,extracted the eigenmatrix from the two dimensions of time and variable,and then used GMM to cluster the eigenmatrix from the perspective of probability distribution.The experimental results demonstrate that the new algorithm can gain better clustering results on MTS.