Time-series classification with SAFE: Simple and fast segmented word embedding-based neural time series classifier

作者：

Highlights：

• In the paper, a dictionary-based method for time series classification is proposed.

• The new method uses SAX to produce symbolic time series representation.

• The core of the model is an embedding layer neural network.

• The network is trained to classify time series converted to sequences of terms.

• The method provides highly satisfying results.

摘要

•In the paper, a dictionary-based method for time series classification is proposed.•The new method uses SAX to produce symbolic time series representation.•The core of the model is an embedding layer neural network.•The network is trained to classify time series converted to sequences of terms.•The method provides highly satisfying results.

论文关键词：Time series,Classification,Word embedding,Neural network

论文评审过程：Received 26 November 2021, Revised 14 July 2022, Accepted 20 July 2022, Available online 2 August 2022, Version of Record 2 August 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.103044