Calibration-free sEMG intention recognition via self-supervised pretraining and adversarial domain alignment for upper-limb rehabilitation

Abstract Accurate calibration-free recognition of upper-limb motion intention from surface EMG (sEMG) is essential for practical rehabilitation robotics. We propose a unified framework that couples self-supervised temporal–spectral pretraining with adversarial domain alignment. First, a masked time–...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Yuanbo Yang, Hiu Hong Teo, Yeong Jin King, Yao Zhang, Gang Wang, Xiangxu Qu
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Nature Portfolio 2025-12-01
Schriftenreihe:	Scientific Reports
Schlagworte:	Surface electromyography (sEMG) Motion intention recognition Self-supervised learning Domain adaptation Calibration-free Upper-limb rehabilitation
Online-Zugang:	https://doi.org/10.1038/s41598-025-28302-0
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!