sEMG-Driven Hand Dynamics Estimation With Incremental Online Learning on a Parallel Ultra-Low-Power Microcontroller

Surface electromyography (sEMG) is a State-of-the-Art (SoA) sensing modality for non-invasive human-machine interfaces for consumer, industrial, and rehabilitation use cases. The main limitation of the current sEMG-driven control policies is the sEMG's inherent variability, especially cross-ses...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on biomedical circuits and systems Ročník 18; číslo 4; s. 810 - 820
Hlavní autori:	Zanghieri, Marcello, Rapa, Pierangelo Maria, Orlandi, Mattia, Donati, Elisa, Benini, Luca, Benatti, Simone
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 01.08.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Accuracy Adult Biomechanical Phenomena Continual learning Datasets Deep Learning Distance learning Electromyography embedded Female Fingers Hand Hand (anatomy) Hand - physiology Human computer interaction human-machine interaction human-machine interfaces Humans Incremental learning Kinematics Latency low-power Machine Learning Male Man-machine interfaces microcontroller Microcontrollers on-device learning Online instruction online learning parallel computing Power management prosthetics PULP Real time regression Signal Processing, Computer-Assisted Simultaneous discrimination learning temporal convolutional networks Tiny machine learning tinyML Training training-on-device ultra-low power
ISSN:	1932-4545, 1940-9990, 1940-9990
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Surface electromyography (sEMG) is a State-of-the-Art (SoA) sensing modality for non-invasive human-machine interfaces for consumer, industrial, and rehabilitation use cases. The main limitation of the current sEMG-driven control policies is the sEMG's inherent variability, especially cross-session due to sensor repositioning; this limits the generalization of the Machine/Deep Learning (ML/DL) in charge of the signal-to-command mapping. The other hot front on the ML/DL side of sEMG-driven control is the shift from the classification of fixed hand positions to the regression of hand kinematics and dynamics, promising a more versatile and fluid control. We present an incremental online-training strategy for sEMG-based estimation of simultaneous multi-finger forces, using a small Temporal Convolutional Network suitable for embedded learning-on-device. We validate our method on the HYSER dataset, cross-day. Our incremental online training reaches a cross-day Mean Absolute Error (MAE) of (9.58 ± 3.89)% of the Maximum Voluntary Contraction on HYSER's RANDOM dataset of improvised, non-predefined force sequences, which is the most challenging and closest to real scenarios. This MAE is on par with an accuracy-oriented, non-embeddable offline training exploiting more epochs. Further, we demonstrate that our online training approach can be deployed on the GAP9 ultra-low power microcontroller, obtaining a latency of 1.49 ms and an energy draw of just 40.4 uJ per forward-backward-update step. These results show that our solution fits the requirements for accurate and real-time incremental training-on-device.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1932-4545 1940-9990 1940-9990
DOI:	10.1109/TBCAS.2024.3415392