A temporal convolutional recurrent autoencoder based framework for compressing time series data

Zhong Zheng, Zijun Zhang

Abstract: Highlights•A novel deep learning based framework for compressing long time series is proposed.•A temporal convolutional network encoder is developed to learn latent representations.•Two decoders are built to restore time series considering short and long range correlations.•A selection scheme is developed for choosing deep structures in time series compression.•An improvement of time series compression performance is achieved.