A deep neural network approach to QRS detection using autoencoders

作者：

Highlights：

• Stacked Autoencoders are very efficient in encoding QRS waves.

• Automatic features are extracted from ECG by deep neural network architecture.

• The developed architecture for QRS detection is comparable to state-of-the-art algorithms on many datasets.

• The proposed method outperforms all deep neural networks in terms of execution time.

摘要

•Stacked Autoencoders are very efficient in encoding QRS waves.•Automatic features are extracted from ECG by deep neural network architecture.•The developed architecture for QRS detection is comparable to state-of-the-art algorithms on many datasets.•The proposed method outperforms all deep neural networks in terms of execution time.

论文关键词：ECG,Deep learning,Stacked autoencoder,QRS detection

论文评审过程：Received 9 September 2020, Revised 29 June 2021, Accepted 29 June 2021, Available online 14 July 2021, Version of Record 16 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115528