Related Experiment Video
Updated: Aug 8, 2026
09:27
An Emerging Target Paradigm to Evoke Fast Visuomotor Responses on Human Upper Limb Muscles
Published on: August 25, 2020
Machine Learning Methods to Predict Unmeasured Muscle Activation in Upper Limb Reaching Task for Assessing
Baivab Bhandari1, Shadman Tahmid2, James Yang1
1Human-Centric Design Research Lab, Department of Mechanical Engineering, Texas Tech University, Lubbock, TX 79409, USA.
Journal of Biomechanical Engineering
|August 7, 2026
Summary
This study introduces a deep learning framework to predict muscle activation using surface electromyography (sEMG) alone. The CNN-LSTM model accurately estimates muscle activation patterns, advancing non-invasive neuromuscular modeling.
Area of Science:
- Biomechanics
- Neuroscience
- Machine Learning
Background:
- Estimating muscle activation is crucial for neuromuscular modeling but challenging due to sensor limitations and complex surface electromyography (sEMG) signals.
- Traditional methods like Inverse Dynamics and Static Optimization require extensive kinematic and kinetic data, limiting their applicability.
- Interpreting direct muscle activation from sEMG is difficult due to signal complexity and non-linearity.
Purpose of the Study:
- To develop and validate a deep learning framework for learning generalizable inter-muscular activation relationships using only sEMG data.
- To assess the effectiveness of different deep learning architectures (CNN, LSTM, CNN-LSTM) in capturing spatial and temporal dynamics of EMG.
- To investigate the impact of dataset size and input muscle selection on prediction accuracy.
Main Methods:
- A deep learning framework was proposed, utilizing sEMG data from 30 participants performing a standardized forward-reaching task.
- Three model architectures were evaluated: Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and hybrid CNN-LSTM models.
- Model performance was assessed by varying the number of unmeasured output muscles, training dataset size, and employing Leave-One-Muscle-Out (LOMO) analysis.
Main Results:
- The hybrid CNN-LSTM model demonstrated superior performance compared to standalone CNN and LSTM models, especially for multi-muscle prediction.
- The CNN-LSTM model achieved high accuracy (RMSE=0.103, r=0.866) in predicting the activation of the triceps long head muscle.
- Analysis confirmed the feasibility of predicting muscle activation patterns using sEMG alone and highlighted the importance of input muscles.
Conclusions:
- Deep learning, particularly the CNN-LSTM architecture, offers a feasible and scalable approach for non-invasive prediction of muscle activation patterns.
- This framework can simultaneously predict activation for superficial muscles and potentially proxy-predict for muscles difficult to measure directly.
- The study provides a foundation for advancing neuromuscular modeling through advanced machine learning techniques applied to sEMG data.
