EMGSense

EMGSense: A Low-Effort Self-Supervised Domain Adaptation Framework for EMG Sensing

Duan, Di (Shenzhen Research Institute; City University of Hong Kong)
Yang, Huanqi (Shenzhen Research Institute; City University of Hong Kong)
Lan, G. (TU Delft Embedded Systems)
Li, Tianxing (Michigan State University)
Jia, Xiaohua (Shenzhen Research Institute; City University of Hong Kong)
Xu, Weitao (City University of Hong Kong; Shenzhen Research Institute)

2023

This paper presents EMGSense, a low-effort self-supervised domain adaptation framework for sensing applications based on Electromyography (EMG). EMGSense addresses one of the fundamental challenges in EMG cross-user sensing—the significant performance degradation caused by time-varying biological heterogeneity—in a low-effort (data-efficient and label-free) manner. To alleviate the burden of data collection and avoid labor-intensive data annotation, we propose two EMG-specific data augmentation methods to simulate the EMG signals generated in various conditions and scope the exploration in label-free scenarios. We model combating biological heterogeneity-caused performance degradation as a multi-source domain adaptation problem that can learn from the diversity among source users to eliminate EMG heterogeneous biological features. To relearn the target-user-specific biological features from the unlabeled data, we integrate advanced self-supervised techniques into a carefully designed deep neural network (DNN) structure. The DNN structure can seamlessly perform two training stages that complement each other to adapt to a new user with satisfactory performance. Comprehensive evaluations on two sizable datasets collected from 13 participants indicate that EMGSense achieves an average accuracy of 91.9% and 81.2% in gesture recognition and activity recognition, respectively. EMGSense outperforms the state-of-the-art EMG-oriented domain adaptation approaches by 12.5%-17.4% and achieves a comparable performance with the one trained in a supervised learning manner.

EMG sensing
biological heterogeneity
domain adaptation
self-supervised learning

http://resolver.tudelft.nl/uuid:e83889c7-ffc0-4d1a-966f-89e87e0cfa0d

https://doi.org/10.1109/PERCOM56429.2023.10099164

IEEE, Danvers

2023-10-18

978-1-6654-5379-0

Proceedings of the 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom)

2023 IEEE International Conference on Pervasive Computing and Communications (PerCom), 2023-03-13 → 2023-03-17, Atlanta, United States

2023 IEEE International Conference on Pervasive Computing and Communications, PerCom 2023

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2023 Di Duan, Huanqi Yang, G. Lan, Tianxing Li, Xiaohua Jia, Weitao Xu