Learning a Hand Model From Dynamic Movements Using High-Density EMG and Convolutional Neural Networks
IEEE Transactions on Biomedical Engineering · 2024-12 · 71 (12) · 3556-3568
DOI: 10.1109/tbme.2024.3432800 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2024-12. Verfasst von Raul C Simpetru und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Electromyography, Hand, Signal Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bavarian Ministry of Economic Affairs, Regional Development and Energy, European Research Council.
Abstract (Originalsprache)
OBJECTIVE: Surface electromyography (sEMG) can sense the motor commands transmitted to the muscles. This work presents a deep learning method that can decode the electrophysiological activity of the forearm muscles into the movements of the human hand. METHODS: We have recorded the kinematics and kinetics of the hand during a wide range of grasps and individual digit movements that cover 22 degrees of freedom of the hand at slow (0.5 Hz) and comfortable (1.5 Hz) movement speeds in 13 healthy participants. The input of the model consists of 320 non-invasive EMG sensors placed on the extrinsic hand muscles. RESULTS: Our network achieves accurate continuous estimation of both kinematics and kinetics, surpassing the performance of comparable networks reported in the literature. By examining the latent space of the network, we find evidence that it mapped EMG activity into the anatomy of the hand at the individual digit level. In contrast to what is observed from the low-pass filtered EMG and linear decoding approaches, we found that the full-bandwidth EMG (monopolar unfiltered) signals during synergistic and individual digit movements contain distinct neural embeddings that encode each movement of the human hand. These manifolds consistently represent the anatomy of the hand and are generalized across participants. Moreover, we found a task-specific distribution of the embeddings without any presence of correlated activations during multi- and individual-digit tasks. CONCLUSION/SIGNIFICANCE: The proposed method could advance the control of assistive hand devices by providing a robust and intuitive interface between muscle signals and hand movements.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Bavarian Ministry of Economic Affairs
- Regional Development and Energy
- European Research Council
- GRASPAGAIN
- German Federal Ministry of Education and Research
- MYOREHAB
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Simpetru, R. C., Arkudas, A., Braun, D. I., Osswald, M., de Oliveira, D. S., Eskofier, B., Kinfe, T. M., & Vecchio, A. D. (2024). Learning a Hand Model From Dynamic Movements Using High-Density EMG and Convolutional Neural Networks. IEEE Transactions on Biomedical Engineering, 71(12), 3556-3568. https://doi.org/10.1109/tbme.2024.3432800
Vancouver
Simpetru RC, Arkudas A, Braun DI, Osswald M, de Oliveira DS, Eskofier B, et al. Learning a Hand Model From Dynamic Movements Using High-Density EMG and Convolutional Neural Networks. IEEE Transactions on Biomedical Engineering. 2024;71(12):3556-3568. doi:10.1109/tbme.2024.3432800
BibTeX
@article{Simpetru2024,
author = {Simpetru, Raul C and Arkudas, Andreas and Braun, Dominik I and Osswald, Marius and de Oliveira, Daniela Souza and Eskofier, Bjoern and Kinfe, Thomas M and Vecchio, Alessandro Del},
title = {Learning a Hand Model From Dynamic Movements Using High-Density EMG and Convolutional Neural Networks},
journal = {IEEE Transactions on Biomedical Engineering},
year = {2024},
volume = {71},
number = {12},
pages = {3556--3568},
doi = {10.1109/tbme.2024.3432800}
}
EUVIMED