Towards Control of a Transhumeral Prosthesis with EEG Signals
Robotic prostheses are expected to allow amputees greater freedom and mobility. However, available options to control transhumeral prostheses are reduced with increasing amputation level. In addition, for electromyography-based control of prostheses, the residual muscles alone cannot generate suffic...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-03-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2306-5354/5/2/26 |
| _version_ | 1797765198949384192 |
|---|---|
| author | D.S.V. Bandara Jumpei Arata Kazuo Kiguchi |
| author_facet | D.S.V. Bandara Jumpei Arata Kazuo Kiguchi |
| author_sort | D.S.V. Bandara |
| collection | DOAJ |
| description | Robotic prostheses are expected to allow amputees greater freedom and mobility. However, available options to control transhumeral prostheses are reduced with increasing amputation level. In addition, for electromyography-based control of prostheses, the residual muscles alone cannot generate sufficiently different signals for accurate distal arm function. Thus, controlling a multi-degree of freedom (DoF) transhumeral prosthesis is challenging with currently available techniques. In this paper, an electroencephalogram (EEG)-based hierarchical two-stage approach is proposed to achieve multi-DoF control of a transhumeral prosthesis. In the proposed method, the motion intention for arm reaching or hand lifting is identified using classifiers trained with motion-related EEG features. For this purpose, neural network and k-nearest neighbor classifiers are used. Then, elbow motion and hand endpoint motion is estimated using a different set of neural-network-based classifiers, which are trained with motion information recorded using healthy subjects. The predictions from the classifiers are compared with residual limb motion to generate a final prediction of motion intention. This can then be used to realize multi-DoF control of a prosthesis. The experimental results show the feasibility of the proposed method for multi-DoF control of a transhumeral prosthesis. This proof of concept study was performed with healthy subjects. |
| first_indexed | 2024-03-12T20:07:21Z |
| format | Article |
| id | doaj.art-5ee28b42c30d4931ac7f0e2e8a3dd293 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-12T20:07:21Z |
| publishDate | 2018-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-5ee28b42c30d4931ac7f0e2e8a3dd2932023-08-02T01:59:36ZengMDPI AGBioengineering2306-53542018-03-01522610.3390/bioengineering5020026bioengineering5020026Towards Control of a Transhumeral Prosthesis with EEG SignalsD.S.V. Bandara0Jumpei Arata1Kazuo Kiguchi2System Engineering Laboratory, Department of Mechanical Engineering, Kyushu University, Fukuoka 819-0395, JapanSystem Engineering Laboratory, Department of Mechanical Engineering, Kyushu University, Fukuoka 819-0395, JapanSystem Engineering Laboratory, Department of Mechanical Engineering, Kyushu University, Fukuoka 819-0395, JapanRobotic prostheses are expected to allow amputees greater freedom and mobility. However, available options to control transhumeral prostheses are reduced with increasing amputation level. In addition, for electromyography-based control of prostheses, the residual muscles alone cannot generate sufficiently different signals for accurate distal arm function. Thus, controlling a multi-degree of freedom (DoF) transhumeral prosthesis is challenging with currently available techniques. In this paper, an electroencephalogram (EEG)-based hierarchical two-stage approach is proposed to achieve multi-DoF control of a transhumeral prosthesis. In the proposed method, the motion intention for arm reaching or hand lifting is identified using classifiers trained with motion-related EEG features. For this purpose, neural network and k-nearest neighbor classifiers are used. Then, elbow motion and hand endpoint motion is estimated using a different set of neural-network-based classifiers, which are trained with motion information recorded using healthy subjects. The predictions from the classifiers are compared with residual limb motion to generate a final prediction of motion intention. This can then be used to realize multi-DoF control of a prosthesis. The experimental results show the feasibility of the proposed method for multi-DoF control of a transhumeral prosthesis. This proof of concept study was performed with healthy subjects.http://www.mdpi.com/2306-5354/5/2/26electroencephalographymotion intentiontranshumeral prosthesiswearable robotbrain computer interface |
| spellingShingle | D.S.V. Bandara Jumpei Arata Kazuo Kiguchi Towards Control of a Transhumeral Prosthesis with EEG Signals Bioengineering electroencephalography motion intention transhumeral prosthesis wearable robot brain computer interface |
| title | Towards Control of a Transhumeral Prosthesis with EEG Signals |
| title_full | Towards Control of a Transhumeral Prosthesis with EEG Signals |
| title_fullStr | Towards Control of a Transhumeral Prosthesis with EEG Signals |
| title_full_unstemmed | Towards Control of a Transhumeral Prosthesis with EEG Signals |
| title_short | Towards Control of a Transhumeral Prosthesis with EEG Signals |
| title_sort | towards control of a transhumeral prosthesis with eeg signals |
| topic | electroencephalography motion intention transhumeral prosthesis wearable robot brain computer interface |
| url | http://www.mdpi.com/2306-5354/5/2/26 |
| work_keys_str_mv | AT dsvbandara towardscontrolofatranshumeralprosthesiswitheegsignals AT jumpeiarata towardscontrolofatranshumeralprosthesiswitheegsignals AT kazuokiguchi towardscontrolofatranshumeralprosthesiswitheegsignals |