A long short-term recurrent spatial-temporal fusion for myoelectric pattern recognition

作者：

Highlights：

• Deep learning concepts borrowed for building a powerful feature extraction framework.

• A novel recurrent spatial-temporal fusion demonstrates a significant performance.

• A bi-directional framework is also proposed equipped with simple TD features.

• Results are benchmarked against several algorithms across 82 subjects.

• RSTF significantly outperforms all other methods, including LSTM and BiLSTM.

摘要

•Deep learning concepts borrowed for building a powerful feature extraction framework.•A novel recurrent spatial-temporal fusion demonstrates a significant performance.•A bi-directional framework is also proposed equipped with simple TD features.•Results are benchmarked against several algorithms across 82 subjects.•RSTF significantly outperforms all other methods, including LSTM and BiLSTM.

论文关键词：Electromyogram,Pattern recognition,LSTM,Feature extraction,Temporal-spatial correlations

论文评审过程：Received 15 May 2020, Revised 27 January 2021, Accepted 27 March 2021, Available online 6 April 2021, Version of Record 21 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114977