Related Experiment Video
Updated: Jun 27, 2025
06:31
Force and Position Control in Humans - The Role of Augmented Feedback
Published on: June 19, 2016
7.8K
Context-informed incremental learning improves both the performance and resilience of myoelectric control
Evan Campbell1, Ethan Eddy2,3, Scott Bateman3
1Institute of Biomedical Engineering, University of new Brunswick, Dineen Dr., Fredericton, NB, E3B 5A3, Canada. ecampbe2@unb.ca.
Journal of Neuroengineering and Rehabilitation
|May 3, 2024
Summary
This study introduces Context-Informed Incremental Learning (CIIL) to improve myoelectric control robustness. CIIL significantly outperforms existing methods, reducing recalibration needs and enhancing user experience for prosthetic devices.
Area of Science:
- Biomedical Engineering
- Rehabilitation Engineering
- Machine Learning
Background:
- Myoelectric control for prosthetics faces robustness issues, leading to performance degradation and frequent recalibration.
- Current unsupervised adaptation methods can worsen performance if they adapt based on incorrect predictions.
- Existing systems often require tedious recalibration, causing user frustration and device abandonment.
Purpose of the Study:
- To propose and evaluate a novel adaptive learning strategy, Context-Informed Incremental Learning (CIIL), for robust myoelectric control.
- To address limitations of current unsupervised adaptation techniques in maintaining performance over time.
- To reduce the need for manual recalibration and improve the real-time control of prosthetic devices.
Main Methods:
- Developed and implemented Context-Informed Incremental Learning (CIIL) strategies.
- Evaluated CIIL in an online target acquisition task under conditions of limited training data and significant input space alteration (45-degree electrode shift).
- Compared CIIL performance against state-of-the-art unsupervised high-confidence adaptation and conventional screen-guided training with 32 participants.
Main Results:
- CIIL strategies significantly outperformed current state-of-the-art unsupervised adaptation methods.
- CIIL demonstrated superior performance compared to conventional training, even after a 45-degree electrode shift.
- The proposed method showed effectiveness in scenarios with limited initial training data and drastic input changes.
Conclusions:
- CIIL offers a robust solution for myoelectric control, overcoming limitations of existing unsupervised adaptation methods.
- This novel strategy has substantial implications for reducing training burden and improving the reliability of prosthetic devices.
- CIIL has the potential to enhance real-time control and user experience in myoelectric applications.
Related Concept Videos
01:10Control Systems
1.1K
Control systems are everywhere in contemporary society, influencing diverse applications from aerospace to automated manufacturing. These systems can be found naturally within biological processes, such as blood sugar regulation and heart rate adjustment in response to stress, as well as in man-made systems like elevators and automated vehicles. A control system is essentially a network of subsystems and processes that collaboratively convert specific inputs into desired outputs.
At the heart...
At the heart...
1.1K
01:20Motor Unit Stimulation
1.5K
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...
1.5K