We are excited to announce that the following paper by Seitaro Yoneda (doctoral student) as the first author has been accepted by IEEE Transactions on Neural Systems and Rehabilitation Engineering!
Seitaro Yoneda and Akira Furui
Adaptive EMG Pattern Classification via Probabilistic Knowledge Transfer with Scale Mixture-Based Bayesian Sequential Learning
IEEE Transactions on Neural Systems and Rehabilitation Engineering (accepted).
This research proposes a novel adaptive method for EMG-based motion recognition that addresses temporal signal variations caused by muscle fatigue and electrode shift. By combining a scale mixture classification model (SMCM) with Bayesian sequential self-training (BSST), the proposed approach can continuously adapt to signal changes without storing historical data. Evaluation experiments, including a 30-day long-term study, demonstrated superior performance in both classification accuracy and confidence estimation compared to conventional methods.
This is Yoneda's first international journal paper and will form part of his doctoral dissertation in the future.