Imperial College London
Portrait Picture

DrPaulBentley

Faculty of Medicine, Department of Brain Sciences

Senior Clinical Research Fellow
 
 
 
//

Contact

 

p.bentley

 
 
//

Location

 

10L21Charing Cross HospitalCharing Cross Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Clarke:2021:10.1109/TBME.2020.3006508,
author = {Clarke, AK and Atashzar, SF and Vecchio, AD and Barsakcioglu, D and Muceli, S and Bentley, P and Urh, F and Holobar, A and Farina, D},
doi = {10.1109/TBME.2020.3006508},
journal = {IEEE Transactions on Biomedical Engineering},
pages = {526--534},
title = {Deep learning for robust decomposition of high-density surface EMG signals},
url = {http://dx.doi.org/10.1109/TBME.2020.3006508},
volume = {68},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.
AU  - Clarke,AK
AU  - Atashzar,SF
AU  - Vecchio,AD
AU  - Barsakcioglu,D
AU  - Muceli,S
AU  - Bentley,P
AU  - Urh,F
AU  - Holobar,A
AU  - Farina,D
DO  - 10.1109/TBME.2020.3006508
EP  - 534
PY  - 2021///
SN  - 0018-9294
SP  - 526
TI  - Deep learning for robust decomposition of high-density surface EMG signals
T2  - IEEE Transactions on Biomedical Engineering
UR  - http://dx.doi.org/10.1109/TBME.2020.3006508
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000611114200014&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://ieeexplore.ieee.org/document/9132652
UR  - http://hdl.handle.net/10044/1/86630
VL  - 68
ER  -
Download