Feature extraction and selection for myoelectric control based on wearable EMG sensors
- Publication Type:
- Journal Article
- Citation:
- Sensors (Switzerland), 2018, 18 (5)
- Issue Date:
- 2018-05-18
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Full metadata record
Field | Value | Language |
---|---|---|
dc.contributor.author | Phinyomark, A | en_US |
dc.contributor.author |
Khushaba, RN |
en_US |
dc.contributor.author | Scheme, E | en_US |
dc.date.available | 2018-05-16 | en_US |
dc.date.issued | 2018-05-18 | en_US |
dc.identifier.citation | Sensors (Switzerland), 2018, 18 (5) | en_US |
dc.identifier.issn | 1424-8220 | en_US |
dc.identifier.uri | http://hdl.handle.net/10453/131892 | |
dc.description.abstract | © 2018 by the authors. Licensee MDPI, Basel, Switzerland. Specialized myoelectric sensors have been used in prosthetics for decades, but, with recent advancements in wearable sensors, wireless communication and embedded technologies, wearable electromyographic (EMG) armbands are now commercially available for the general public. Due to physical, processing, and cost constraints, however, these armbands typically sample EMG signals at a lower frequency (e.g., 200 Hz for the Myo armband) than their clinical counterparts. It remains unclear whether existing EMG feature extraction methods, which largely evolved based on EMG signals sampled at 1000 Hz or above, are still effective for use with these emerging lower-bandwidth systems. In this study, the effects of sampling rate (low: 200 Hz vs. high: 1000 Hz) on the classification of hand and finger movements were evaluated for twenty-six different individual features and eight sets of multiple features using a variety of datasets comprised of both able-bodied and amputee subjects. The results show that, on average, classification accuracies drop significantly (p < 0.05) from 2% to 56% depending on the evaluated features when using the lower sampling rate, and especially for transradial amputee subjects. Importantly, for these subjects, no number of existing features can be combined to compensate for this loss in higher-frequency content. From these results, we identify two new sets of recommended EMG features (along with a novel feature, L-scale) that provide better performance for these emerging low-sampling rate systems. | en_US |
dc.relation.ispartof | Sensors (Switzerland) | en_US |
dc.relation.isbasedon | 10.3390/s18051615 | en_US |
dc.subject.classification | Analytical Chemistry | en_US |
dc.subject.mesh | Hand | en_US |
dc.subject.mesh | Humans | en_US |
dc.subject.mesh | Electromyography | en_US |
dc.subject.mesh | Biosensing Techniques | en_US |
dc.subject.mesh | Prostheses and Implants | en_US |
dc.subject.mesh | Movement | en_US |
dc.subject.mesh | Pattern Recognition, Automated | en_US |
dc.subject.mesh | Amputees | en_US |
dc.subject.mesh | Female | en_US |
dc.subject.mesh | Male | en_US |
dc.subject.mesh | Wearable Electronic Devices | en_US |
dc.subject.mesh | Hand | en_US |
dc.subject.mesh | Humans | en_US |
dc.subject.mesh | Electromyography | en_US |
dc.subject.mesh | Biosensing Techniques | en_US |
dc.subject.mesh | Prostheses and Implants | en_US |
dc.subject.mesh | Movement | en_US |
dc.subject.mesh | Pattern Recognition, Automated | en_US |
dc.subject.mesh | Amputees | en_US |
dc.subject.mesh | Female | en_US |
dc.subject.mesh | Male | en_US |
dc.subject.mesh | Wearable Electronic Devices | en_US |
dc.subject.mesh | Amputees | en_US |
dc.subject.mesh | Biosensing Techniques | en_US |
dc.subject.mesh | Electromyography | en_US |
dc.subject.mesh | Female | en_US |
dc.subject.mesh | Hand | en_US |
dc.subject.mesh | Humans | en_US |
dc.subject.mesh | Male | en_US |
dc.subject.mesh | Movement | en_US |
dc.subject.mesh | Pattern Recognition, Automated | en_US |
dc.subject.mesh | Prostheses and Implants | en_US |
dc.subject.mesh | Wearable Electronic Devices | en_US |
dc.title | Feature extraction and selection for myoelectric control based on wearable EMG sensors | en_US |
dc.type | Journal Article | |
utslib.description.version | Published | en_US |
utslib.citation.volume | 5 | en_US |
utslib.citation.volume | 18 | en_US |
utslib.for | 0906 Electrical and Electronic Engineering | en_US |
utslib.for | 0301 Analytical Chemistry | en_US |
utslib.for | 0906 Electrical and Electronic Engineering | en_US |
utslib.for | 0502 Environmental Science and Management | en_US |
utslib.for | 0602 Ecology | en_US |
pubs.embargo.period | Not known | en_US |
pubs.organisational-group | /University of Technology Sydney | |
pubs.organisational-group | /University of Technology Sydney/Faculty of Engineering and Information Technology | |
pubs.organisational-group | /University of Technology Sydney/Faculty of Engineering and Information Technology/School of Biomedical Engineering | |
utslib.copyright.status | open_access | |
pubs.issue | 5 | en_US |
pubs.publication-status | Published | en_US |
pubs.volume | 18 | en_US |
Abstract:
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. Specialized myoelectric sensors have been used in prosthetics for decades, but, with recent advancements in wearable sensors, wireless communication and embedded technologies, wearable electromyographic (EMG) armbands are now commercially available for the general public. Due to physical, processing, and cost constraints, however, these armbands typically sample EMG signals at a lower frequency (e.g., 200 Hz for the Myo armband) than their clinical counterparts. It remains unclear whether existing EMG feature extraction methods, which largely evolved based on EMG signals sampled at 1000 Hz or above, are still effective for use with these emerging lower-bandwidth systems. In this study, the effects of sampling rate (low: 200 Hz vs. high: 1000 Hz) on the classification of hand and finger movements were evaluated for twenty-six different individual features and eight sets of multiple features using a variety of datasets comprised of both able-bodied and amputee subjects. The results show that, on average, classification accuracies drop significantly (p < 0.05) from 2% to 56% depending on the evaluated features when using the lower sampling rate, and especially for transradial amputee subjects. Importantly, for these subjects, no number of existing features can be combined to compensate for this loss in higher-frequency content. From these results, we identify two new sets of recommended EMG features (along with a novel feature, L-scale) that provide better performance for these emerging low-sampling rate systems.
Please use this identifier to cite or link to this item:
Download statistics for the last 12 months
Not enough data to produce graph