Sökning: onr:"swepub:oai:research.chalmers.se:8d6a6be3-8903-42c8-acdc-92f0dfa19cf2" >
Deep learning for r...
Deep learning for robust decomposition of high-density surface EMG signals
-
- Clarke, Alexander Kenneth (författare)
- Imperial College of Science, Technology and Medicine
-
- Atashzar, S. Farokh (författare)
- New York University
-
- Vecchio, Alessandro Del (författare)
- Imperial College of Science, Technology and Medicine
-
visa fler...
-
- Barsakcioglu, Deren (författare)
- Imperial College of Science, Technology and Medicine
-
- Muceli, Silvia, 1981 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Bentley, Paul (författare)
- Imperial College of Science, Technology and Medicine
-
- Urh, Filip (författare)
- Univerza v Mariboru,University of Maribor
-
- Holobar, Ales (författare)
- Univerza v Mariboru,University of Maribor
-
- Farina, Dario (författare)
- Imperial College of Science, Technology and Medicine
-
visa färre...
-
(creator_code:org_t)
- 2021
- 2021
- Engelska.
-
Ingår i: IEEE Transactions on Biomedical Engineering. - 0018-9294 .- 1558-2531. ; 68:2, s. 526-534
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://research.cha...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Medicinteknik -- Annan medicinteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Medical Engineering -- Other Medical Engineering (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)
Nyckelord
- neural drive to muscle
- Motor unit
- deep learning
- blind source separation
- recurrent neural network
Publikations- och innehållstyp
- art (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas
- Av författaren/redakt...
-
Clarke, Alexande ...
-
Atashzar, S. Far ...
-
Vecchio, Alessan ...
-
Barsakcioglu, De ...
-
Muceli, Silvia, ...
-
Bentley, Paul
-
visa fler...
-
Urh, Filip
-
Holobar, Ales
-
Farina, Dario
-
visa färre...
- Om ämnet
-
- TEKNIK OCH TEKNOLOGIER
-
TEKNIK OCH TEKNO ...
-
och Medicinteknik
-
och Annan medicintek ...
-
- NATURVETENSKAP
-
NATURVETENSKAP
-
och Data och informa ...
-
och Bioinformatik
-
- TEKNIK OCH TEKNOLOGIER
-
TEKNIK OCH TEKNO ...
-
och Elektroteknik oc ...
-
och Signalbehandling
- Artiklar i publikationen
-
IEEE Transaction ...
- Av lärosätet
-
Chalmers tekniska högskola