A hybrid modeling structure composed of a one degree of freedom computational musculo-skeletal model and a multilayer perceptron neural network was used to effectively map electromyography (EMG) from a human exercise trial to muscle activations in a physiologically feasible and accurate fashion. Several configurations of the complete hybrid system were used to map four muscle surface EMGs from a ballistic elbow flexion to normalized muscle activations, estimated individual muscle forces and torque about the joint. The net joint torque was used to train the neural portion of the hybrid system to minimize kinematic error. The model allowed the estimation of the nonobservable parameters: normalized muscle activations and forces which was used to penalize the learning system. With these parameters in the learning equation, our system produced muscle activations consistent with the classic triphasic response present in ballistic movements.
Skip Nav Destination
Article navigation
June 1997
Technical Briefs
A Neural Network Approach to Electromyographic Signal Processing for a Motor Control Task
W. T. Lester,
W. T. Lester
The University of Texas at Austin, Mechanical Engineering, ETC II 3.104, Austin, TX 78712
Search for other works by this author on:
R. V. Gonzalez,
R. V. Gonzalez
LeTourneau University, Mechanical Engineering, Longview, TX 75602
Search for other works by this author on:
B. Fernandez,
B. Fernandez
The University of Texas at Austin, Mechanical Engineering, ETC II 3.104, Austin, TX 78712
Search for other works by this author on:
R. E. Barr
R. E. Barr
The University of Texas at Austin, Mechanical Engineering, ETC II 3.104, Austin, TX 78712
Search for other works by this author on:
W. T. Lester
The University of Texas at Austin, Mechanical Engineering, ETC II 3.104, Austin, TX 78712
R. V. Gonzalez
LeTourneau University, Mechanical Engineering, Longview, TX 75602
B. Fernandez
The University of Texas at Austin, Mechanical Engineering, ETC II 3.104, Austin, TX 78712
R. E. Barr
The University of Texas at Austin, Mechanical Engineering, ETC II 3.104, Austin, TX 78712
J. Dyn. Sys., Meas., Control. Jun 1997, 119(2): 335-337 (3 pages)
Published Online: June 1, 1997
Article history
Received:
September 23, 1993
Revised:
February 29, 1996
Online:
December 3, 2007
Citation
Lester, W. T., Gonzalez, R. V., Fernandez, B., and Barr, R. E. (June 1, 1997). "A Neural Network Approach to Electromyographic Signal Processing for a Motor Control Task." ASME. J. Dyn. Sys., Meas., Control. June 1997; 119(2): 335–337. https://doi.org/10.1115/1.2801260
Download citation file:
Get Email Alerts
Cited By
Multi Combustor Turbine Engine Acceleration Process Control Law Design
J. Dyn. Sys., Meas., Control
A Distributed Layered Planning and Control Algorithm for Teams of Quadrupedal Robots: An Obstacle-Aware Nonlinear Model Predictive Control Approach
J. Dyn. Sys., Meas., Control (May 2025)
Active Data-Enabled Robot Learning of Elastic Workpiece Interactions
J. Dyn. Sys., Meas., Control (May 2025)
Innovative Pressure Control With ANFIS-Enhanced Mode Switching for High-Speed Pneumatic Systems
J. Dyn. Sys., Meas., Control (May 2025)
Related Articles
Evaluating an Integrated Musculoskeletal Model of the Human Arm
J Biomech Eng (February,1997)
Validation of an EMG-Driven, Graphically Based Isometric Musculoskeletal Model of the Cervical Spine
J Biomech Eng (June,2008)
A Feature-Encoded Physics-Informed Parameter Identification Neural Network for Musculoskeletal Systems
J Biomech Eng (December,2022)
Measurement of Driver Steering Torque Using Electromyography
J. Dyn. Sys., Meas., Control (December,2006)
Related Proceedings Papers
Related Chapters
Fitting a Function and Its Derivative
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17
Estimating Resilient Modulus Using Neural Network Models
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17
A Review for Feature Extraction of EMG Signal Processing
International Conference on Computer and Automation Engineering, 4th (ICCAE 2012)