Extraction of Multi-Labelled Movement Information from the Raw HD-sEMG Image with Time-Domain Depth
(2019) In Scientific Reports 9(1).- Abstract
In contemporary muscle-computer interfaces for upper limb prosthetics there is often a trade-off between control robustness and range of executable movements. As a very low movement error rate is necessary in practical applications, this often results in a quite severe limitation of controllability; a problem growing ever more salient as the mechanical sophistication of multifunctional myoelectric prostheses continues to improve. A possible remedy for this could come from the use of multi-label machine learning methods, where complex movements can be expressed as the superposition of several simpler movements. Here, we investigate this claim by applying a multi-labeled classification scheme in the form of a deep convolutional neural... (More)
In contemporary muscle-computer interfaces for upper limb prosthetics there is often a trade-off between control robustness and range of executable movements. As a very low movement error rate is necessary in practical applications, this often results in a quite severe limitation of controllability; a problem growing ever more salient as the mechanical sophistication of multifunctional myoelectric prostheses continues to improve. A possible remedy for this could come from the use of multi-label machine learning methods, where complex movements can be expressed as the superposition of several simpler movements. Here, we investigate this claim by applying a multi-labeled classification scheme in the form of a deep convolutional neural network (CNN) to high density surface electromyography (HD-sEMG) recordings. We use 16 independent labels to model the movements of the hand and forearm state, representing its major degrees of freedom. By training the neural network on 16 × 8 sEMG image sequences 24 samples long with a sampling rate of 2048 Hz to detect these labels, we achieved a mean exact match rate of 78.7% and a mean Hamming loss of 2.9% across 14 healthy test subjects. With this, we demonstrate the feasibility of highly versatile and responsive sEMG control interfaces without loss of accuracy.
(Less)
- author
- Olsson, Alexander E. LU ; Sager, Paulina ; Andersson, Elin ; Björkman, Anders LU ; Malešević, Nebojša LU and Antfolk, Christian LU
- organization
- publishing date
- 2019
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Scientific Reports
- volume
- 9
- issue
- 1
- article number
- 7244
- publisher
- Nature Publishing Group
- external identifiers
-
- pmid:31076600
- scopus:85065673406
- ISSN
- 2045-2322
- DOI
- 10.1038/s41598-019-43676-8
- language
- English
- LU publication?
- yes
- id
- dbad3679-af5d-4c5b-8552-2d7012eb645d
- date added to LUP
- 2019-05-27 16:05:33
- date last changed
- 2024-08-06 18:53:21
@article{dbad3679-af5d-4c5b-8552-2d7012eb645d, abstract = {{<p>In contemporary muscle-computer interfaces for upper limb prosthetics there is often a trade-off between control robustness and range of executable movements. As a very low movement error rate is necessary in practical applications, this often results in a quite severe limitation of controllability; a problem growing ever more salient as the mechanical sophistication of multifunctional myoelectric prostheses continues to improve. A possible remedy for this could come from the use of multi-label machine learning methods, where complex movements can be expressed as the superposition of several simpler movements. Here, we investigate this claim by applying a multi-labeled classification scheme in the form of a deep convolutional neural network (CNN) to high density surface electromyography (HD-sEMG) recordings. We use 16 independent labels to model the movements of the hand and forearm state, representing its major degrees of freedom. By training the neural network on 16 × 8 sEMG image sequences 24 samples long with a sampling rate of 2048 Hz to detect these labels, we achieved a mean exact match rate of 78.7% and a mean Hamming loss of 2.9% across 14 healthy test subjects. With this, we demonstrate the feasibility of highly versatile and responsive sEMG control interfaces without loss of accuracy.</p>}}, author = {{Olsson, Alexander E. and Sager, Paulina and Andersson, Elin and Björkman, Anders and Malešević, Nebojša and Antfolk, Christian}}, issn = {{2045-2322}}, language = {{eng}}, number = {{1}}, publisher = {{Nature Publishing Group}}, series = {{Scientific Reports}}, title = {{Extraction of Multi-Labelled Movement Information from the Raw HD-sEMG Image with Time-Domain Depth}}, url = {{http://dx.doi.org/10.1038/s41598-019-43676-8}}, doi = {{10.1038/s41598-019-43676-8}}, volume = {{9}}, year = {{2019}}, }