Unsupervised learning algorithm for time series using bivariate AR(1) model
作者：
Highlights：
• Traditional time series clustering and classification algorithms deal only with univariate time series data.
• Unsupervised learning algorithm for bivariate time series has been developed.
• The initial clusters are found using K-means algorithm.
• The model parameters are estimated using the EM algorithm.
• Bivariate unsupervised learning algorithm gives better clustering results than univariate algorithms.
摘要
•Traditional time series clustering and classification algorithms deal only with univariate time series data.•Unsupervised learning algorithm for bivariate time series has been developed.•The initial clusters are found using K-means algorithm.•The model parameters are estimated using the EM algorithm.•Bivariate unsupervised learning algorithm gives better clustering results than univariate algorithms.
论文关键词：Time series,Clustering,EM algorithm,Autoregressive process
论文评审过程：Available online 5 December 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.11.030
