Deep learning for robust decomposition of high-density surface EMG signals
Journal article, 2021

Blind source separation (BSS) algorithms, such as gradient convolution kernel compensation (gCKC), can efficiently and accurately decompose high-density surface electromyography (HD-sEMG) signals into constituent motor unit (MU) action potential trains. Once the separation matrix is blindly estimated on a signal interval, it is also possible to apply the same matrix to subsequent signal segments. Nonetheless, the trained separation matrices are sub-optimal in noisy conditions and require that incoming data undergo computationally expensive whitening. One unexplored alternative is to instead use the paired HD-sEMG signal and BSS output to train a model to predict MU activations within a supervised learning framework. A gated recurrent unit (GRU) network was trained to decompose both simulated and experimental unwhitened HD-sEMG signal using the output of the gCKC algorithm. The results on the experimental data were validated by comparison with the decomposition of concurrently recorded intramuscular EMG signals. The GRU network outperformed gCKC at low signal-to-noise ratios, proving superior performance in generalising to new data. Using 12 seconds of experimental data per recording, the GRU performed similarly to gCKC, at rates of agreement of 92.5% (84.5%-97.5%) and 94.9% (88.8%-100.0%) respectively for GRU and gCKC against matched intramuscular sources.

neural drive to muscle

Motor unit

deep learning

blind source separation

recurrent neural network

Author

Alexander Kenneth Clarke

Imperial College London

S. Farokh Atashzar

New York University

Alessandro Del Vecchio

Imperial College London

Deren Barsakcioglu

Imperial College London

Silvia Muceli

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Paul Bentley

Imperial College London

Filip Urh

University of Maribor

Ales Holobar

University of Maribor

Dario Farina

Imperial College London

IEEE Transactions on Biomedical Engineering

0018-9294 (ISSN) 15582531 (eISSN)

Vol. 68 2 526-534 9132652

Subject Categories

Other Medical Engineering

Bioinformatics (Computational Biology)

Signal Processing

DOI

10.1109/TBME.2020.3006508

PubMed

32746049

More information

Latest update

3/17/2021