Randomized trees for time series representation and similarity
作者：
Highlights：
• Representation learning is difficult when time series contain irregularities.
• Rand-TS is a time series representation learning framework based on random trees.
• Rand-TS can work with both univariate and multivariate time series.
• Rand-TS can work with time series with varying length and missing information.
• Allows incorporating additional information into the time series representation.
摘要
•Representation learning is difficult when time series contain irregularities.•Rand-TS is a time series representation learning framework based on random trees.•Rand-TS can work with both univariate and multivariate time series.•Rand-TS can work with time series with varying length and missing information.•Allows incorporating additional information into the time series representation.
论文关键词：Time series,Representation learning,Random trees,Classification
论文评审过程：Received 11 August 2020, Revised 7 February 2021, Accepted 3 June 2021, Available online 12 June 2021, Version of Record 1 July 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108097
