Related Experiment Video
Updated: Jun 6, 2026
07:30
The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals
Published on: January 13, 2022
Towards smart prosthetic hand: Adaptive probability based skeletan muscle fatigue model
Parmod Kumar1, Anish Sebastian, Chandrasekhar Potluri
1Measurement and Control Engineering Research Center (MCERC), College of Engineering, Idaho State University, Pocatello, Idaho 83209, USA. kumaparm@isu.edu
Summary
This study improves skeletal muscle force estimation using surface electromyography (sEMG) signals. Optimized filters and a novel fusion method reduce crosstalk and enhance accuracy for muscle dynamics and fatigue modeling.
Area of Science:
- Biomedical Engineering
- Neuroscience
- Biomechanics
Background:
- Surface electromyography (sEMG) is crucial for estimating skeletal muscle force.
- Sensor placement near motor units is common but leads to signal crosstalk.
- Accurate muscle force and fatigue modeling requires addressing signal interference.
Purpose of the Study:
- To develop an improved method for estimating skeletal muscle force using sEMG signals.
- To mitigate crosstalk interference between sEMG sensors.
- To enhance the accuracy of muscle fatigue models.
Main Methods:
- Utilized an array of three sEMG sensors to capture muscle dynamics.
- Applied optimized nonlinear Half-Gaussian Bayesian filters and Chebyshev type-II filters.
- Employed Genetic Algorithms for filter optimization and system identification.
- Developed three discrete time state-space muscle fatigue models.
- Fused model outputs using Kullback Information Criterion (KIC) for model selection.
Main Results:
- Successfully filtered sEMG signals and modeled muscle fatigue.
- Genetic Algorithms optimized filter parameters for improved signal processing.
- Kullback Information Criterion enabled probabilistic model selection and fusion.
- Achieved enhanced accuracy in skeletal muscle force estimation.
Conclusions:
- The proposed method effectively reduces sEMG crosstalk and improves force estimation accuracy.
- Optimized filtering and model fusion techniques provide robust muscle dynamics insights.
- This approach offers a significant advancement in non-invasive muscle function assessment.
