A Multi-Scale CNN for Transfer Learning in sEMG-Based Hand Gesture Recognition for Prosthetic Devices
Sensors · 07.11.2024 · 24 (22) · 7147
DOI: 10.3390/s24227147 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 07.11.2024. Verfasst von Riccardo Fratti und 5 weiteren Autor:innen. Beteiligte Einrichtung: Informatics Institute, University of Applied Sciences Western Switzerland (HES-SO Valais), 3960 Sierre, Switzerland. Hauptthemen laut MEDLINE: Electromyography, Gestures, Hand, Neural Networks, Computer. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Advancements in neural network approaches have enhanced the effectiveness of surface Electromyography (sEMG)-based hand gesture recognition when measuring muscle activity. However, current deep learning architectures struggle to achieve good generalization and robustness, often demanding significant computational resources. The goal of this paper was to develop a robust model that can quickly adapt to new users using Transfer Learning. We propose a Multi-Scale Convolutional Neural Network (MSCNN), pre-trained with various strategies to improve inter-subject generalization. These strategies include domain adaptation with a gradient-reversal layer and self-supervision using triplet margin loss. We evaluated these approaches on several benchmark datasets, specifically the NinaPro databases. This study also compared two different Transfer Learning frameworks designed for user-dependent fine-tuning. The second Transfer Learning framework achieved a 97% F1 Score across 14 classes with an average of 1.40 epochs, suggesting potential for on-site model retraining in cases of performance degradation over time. The findings highlight the effectiveness of Transfer Learning in creating adaptive, user-specific models for sEMG-based prosthetic hands. Moreover, the study examined the impacts of rectification and window length, with a focus on real-time accessible normalizing techniques, suggesting significant improvements in usability and performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Informatics Institute, University of Applied Sciences Western Switzerland (HES-SO Valais), 3960 Sierre, Switzerland.
- Department of Neuroscience, University of Padua, 35122 Padua, Italy.
- Medical Informatics, University of Geneva, 1205 Geneva, Switzerland.
- The Sense Innovation and Research Center, 1007 Lausanne, Switzerland.
- Clinic of Plastic Surgery, University Hospital of Padua, 35128 Padova, Italy.
ORCID-Profile: Riccardo Fratti, Niccolò Marini, Manfredo Atzori, Henning Müller, Cesare Tiengo, Franco Bassetto
Zitieren
APA
Fratti, R., Marini, N., Atzori, M., Müller, H., Tiengo, C., & Bassetto, F. (2024). A Multi-Scale CNN for Transfer Learning in sEMG-Based Hand Gesture Recognition for Prosthetic Devices. Sensors, 24(22), 7147. https://doi.org/10.3390/s24227147
Vancouver
Fratti R, Marini N, Atzori M, Müller H, Tiengo C, Bassetto F. A Multi-Scale CNN for Transfer Learning in sEMG-Based Hand Gesture Recognition for Prosthetic Devices. Sensors. 2024;24(22):7147. doi:10.3390/s24227147
BibTeX
@article{Fratti2024,
author = {Fratti, Riccardo and Marini, Niccolò and Atzori, Manfredo and Müller, Henning and Tiengo, Cesare and Bassetto, Franco},
title = {A Multi-Scale CNN for Transfer Learning in sEMG-Based Hand Gesture Recognition for Prosthetic Devices},
journal = {Sensors},
year = {2024},
volume = {24},
number = {22},
pages = {7147},
doi = {10.3390/s24227147}
}
EUVIMED