Neural network classification of myoelectric signal for prosthesis control
M F Kelly1, P A Parker, R N Scott
1Electrical Engineering Department, University of New Brunswick, Fredericton, New Brunswick, Canada; Institute of Biomedical Engineering, University of New Brunswick, Fredericton, New Brunswick, Canada.
Summary
Researchers developed a new method using myoelectric signals (MES) to control prosthetic arms. This technique accurately identifies upper arm muscle contractions for natural prosthetic limb movement.
Area of Science:
- Biomedical Engineering
- Rehabilitation Robotics
- Signal Processing
Background:
- Developing intuitive control for multi-degree of freedom prosthetic arms remains a challenge.
- Myoelectric signals (MES) offer a promising avenue for non-invasive control strategies.
- Existing methods often require extensive user training for pattern recognition.
Purpose of the Study:
- To explore an alternative approach for prosthetic arm control using single-channel MES.
- To identify natural upper arm muscle contraction patterns associated with specific arm functions.
- To enable proportional rate control for prosthetic devices independent of signal power.
Main Methods:
- Analysis of single-channel myoelectric signals (MES) to extract spectral features.
- Classification of four distinct arm functions (elbow flexion/extension, forearm pronation/supination) using these features.
- Implementation of an artificial neural network, specifically three single-layer perceptron networks, for MES classification.
Main Results:
- Successfully identified natural muscle contraction patterns for four key arm functions.
- Achieved an average classification performance of 85% across five subjects.
- Demonstrated the feasibility of power-independent identification for proportional control.
Conclusions:
- Single-channel MES analysis with spectral features and neural networks can effectively classify arm functions.
- This approach facilitates natural, intuitive control for advanced prosthetic arms.
- The method shows potential for improving prosthetic limb functionality and user experience.
More Related Videos
Related Concept Videos
01:20Motor Unit Stimulation
When the neuron of a motor unit fires an action potential, it triggers a series of events, leading to a twitch contraction in the muscle fibers. The process of excitation-contraction coupling is crucial in relaying the action potential to the muscle fibers.
The latent period of contraction marks the onset of excitation-contraction coupling, when the action potential propagates across the sarcolemma, preparing the muscle fibers for contraction. As the fibers enter the contraction phase, the...
The latent period of contraction marks the onset of excitation-contraction coupling, when the action potential propagates across the sarcolemma, preparing the muscle fibers for contraction. As the fibers enter the contraction phase, the...
01:18Hierarchy of Motor Control
The hierarchy of motor control refers to the different levels of organization and processing involved in controlling movement in the body. These levels range from higher cortical areas involved in planning and decision-making to lower spinal cord reflexes that respond automatically to external stimuli.