Related Experiment Video
Updated: Jun 9, 2025
08:48
Combining Multiple Data Acquisition Systems to Study Corticospinal Output and Multi-segment Biomechanics
Published on: January 9, 2016
6.9K
EMG and SSVEP-based bimodal estimation of elbow angle trajectory
Fatemeh Davarinia1, Ali Maleki1
1Biomedical Engineering Department, Semnan University, Semnan, Iran.
Neuroscience
|October 25, 2024
Summary
This study combined electromyogram (EMG) signals and target information to improve human-machine interface performance. Integrating these signals enhances movement trajectory estimation, especially for individuals with impairments.
Area of Science:
- Biomedical Engineering
- Neuroscience
- Rehabilitation Technology
Background:
- Estimating movement trajectories using electromyogram (EMG) signals in human-machine interfaces (HMIs) is challenging, particularly for those with movement impairments.
- Combining EMG with other biological signals and movement information can improve estimation accuracy.
- Assistive devices require robust and accurate trajectory prediction for effective function.
Purpose of the Study:
- To enhance the performance of human-machine interfaces by combining electromyogram (EMG) signals with target information for movement trajectory estimation.
- To investigate the efficacy of a bimodal decoder integrating EMG and target data compared to EMG-only decoders.
- To assess the impact of fatigue on the performance of the proposed bimodal decoder.
Main Methods:
- Recorded EMG activity from shoulder and arm muscles, elbow angle, and electroencephalogram (EEG) signals from ten healthy subjects.
- Utilized steady-state visual evoked potentials (SSVEPs) to recognize the reaching target.
- Developed a bimodal decoder mapping final elbow angle and EMG to elbow angle trajectory, and compared it to an EMG-based decoder.
Main Results:
- The bimodal decoder integrating EMG and final elbow angle information significantly outperformed the EMG-only decoder.
- The proposed structure maintained superior performance even under conditions of increased subject fatigue.
- Incorporating recognized reaching target information improved the estimation accuracy of the reaching profile.
Conclusions:
- Bimodal decoders that integrate EMG and target information offer significant benefits for enhancing human-machine interfaces.
- These findings are highly relevant for improving assistive robotic devices and prostheses, particularly for real-time upper limb rehabilitation.
- The enhanced trajectory estimation can lead to more intuitive and effective control of assistive technologies.
