Journal of Rehabilitation Research & Development (JRRD)

Quick Links

  • Health Programs
  • Protect your health
  • Learn more: A-Z Health
Veterans Crisis Line Badge

JRRD at a Glance

Electromyographic-based neural network control of transhumeral prostheses

Christopher L. Pulliam, MS, et al.

Figure 5. Cross-validated time-delayed artificial neural network prediction performance as function of number of muscles that were provided as input to network. Muscles included were customized to each subject and selected using forward selection method. RMSE = root-mean-square error.

Upper-limb amputation can greatly impairs function of patients, particularly those with above-elbow amputations. Electromyographic (EMG) signals have proven to be effective command sources for controlling externally powered upper-limb prostheses. The work presented here specifically investigates a method for predicting arm movements based on EMG signals from muscles in the upper arm and shoulder. With this approach, a patient may be able to control his or her transhumeral prosthesis more naturally and effortlessly than with current commercially available options.

Volume 48 Number 6, 2011
   Pages 739 — 754

View HTML  ¦  View PDF  ¦  Contents Vol. 48, No. 6
This article and any supplementary material should be cited as follows:
Pulliam CL, Lambrecht JM, Kirsch RF. Electromyogram-based neural network control of transhumeral prostheses.
J Rehabil Res Dev. 2011;48(6):739-54.

Last Reviewed or Updated  Monday, July 11, 2011 9:06 AM

Valid HTML 4.01 Transitional