Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 5 (2)

Towards Control of a Transhumeral Prosthesis With EEG Signals

Affiliations

Towards Control of a Transhumeral Prosthesis With EEG Signals

D S V Bandara et al. Bioengineering (Basel).

Abstract

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.

Keywords: brain computer interface; electroencephalography; motion intention; transhumeral prosthesis; wearable robot.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Proposed Hierarchical Approach.
Figure 2
Figure 2
Proposed approach for motion identification. CAR: common average reference.
Figure 3
Figure 3
Experimental setup. (a) Electrode layout for experiment; (b) Marker setup for motion recording.
Figure 4
Figure 4
Motions used in the experiment. (a) Arm lifting; (b) Hand reaching; (c) Motion schedule (1 = arm lifting motion, 0 = rest, −1 = hand reaching motion).
Figure 5
Figure 5
Feature plots for channel selection. (a) Movement-related cortical potential (MRCP); (b) delta band power; (c) RMS; (d) alpha band power.
Figure 6
Figure 6
Proposed approach for estimation of identified motion (Sn—healthy individuals, n—1, 2, 3, …, Ux—residual limb joint angle of the transhumeral amputee).
Figure 7
Figure 7
Prediction from the system with MRCP for Subject 1 (1 = lifting motion, −1 = reaching motion, 0 = rest, blue line = prediction, orange line = subject motion).
Figure 8
Figure 8
Motion relationships. (a) Elbow flexion/extension angle to the shoulder flexion/extension angle for reaching. (b) Variation of the endpoint with the shoulder flexion/extension angle.
Figure 9
Figure 9
Comparison of data measured experimentally (blue line) and those generated by the neural network classifier (orange line). (a) Estimated elbow flexion/extension angle; Hand trajectory in the (b) x direction and (c) y direction.
Figure 9
Figure 9
Comparison of data measured experimentally (blue line) and those generated by the neural network classifier (orange line). (a) Estimated elbow flexion/extension angle; Hand trajectory in the (b) x direction and (c) y direction.
Figure 10
Figure 10
Summary of the results of the motion intention classifiers (error bars show the standard deviation).

Similar articles

See all similar articles

Cited by 1 PubMed Central articles

References

    1. Schultz A.E., Kuiken T.A. Neural interfaces for control of upper limb prostheses: The state of the art and future possibilities. PM R. 2011;3:55–67. doi: 10.1016/j.pmrj.2010.06.016. - DOI - PubMed
    1. Kundu S.K., Kiguchi K., Horikawa E. Design and Control Strategy for a 5 DOF Above-Elbow Prosthetic Arm. Int. J. Assist. Robot. Mechatron. 2008;9:61–75.
    1. Resnik L., Klinger S.L., Etter K. The DEKA Arm: Its features, functionality, and evolution during the Veterans Affairs Study to optimize the DEKA Arm. Prosthet. Orthot. Int. 2013 doi: 10.1177/0309364613506913. - DOI - PubMed
    1. Lenzi T., Lipsey J., Sensinger J.W. The RIC Arm—A Small Anthropomorphic Transhumeral Prosthesis. IEEE/ASME Trans. Mechatron. 2016;21:2660–2671. doi: 10.1109/TMECH.2016.2596104. - DOI
    1. Fite K.B., Withrow T.J., Shen X., Wait K.W., Mitchell J.E., Goldfarb M. A Gas-Actuated Anthropomorphic Prosthesis for Transhumeral Amputees. IEEE Trans. Robot. 2008;24:159–169. doi: 10.1109/TRO.2007.914845. - DOI
Feedback