Speed-enhanced Subdomain Alignment for Long-term Stable Neural Decoding in Brain-computer Interfaces
BIBM | This paper proposes SeSA, a semi-supervised domain adaptation framework that improves BCI recalibration by aligning both global and speed-specific neural features, achieving robust decoding across days despite neural nonstationarities.
Jan 1, 2024
Tracking functional changes in nonstationary signals with evolutionary ensemble bayesian model for robust neural decoding
NeurIPS | A novel evolutionary ensemble framework, EvoEnsemble, dynamically adapts to changes in neural signals by evolving decoders over time, significantly improving the accuracy and robustness of neural decoding in nonstationary conditions.
Dec 6, 2022
A brain-controlled mahjong game with artificial intelligence augmentation
CICAI | An AI-augmented brain-computer interface is developed for a mahjong game, enabling easier and more precise control by allowing users to select from AI-suggested options, thus improving usability and user experience in a real BCI application.
Aug 27, 2022
Dynamic ensemble bayesian filter for robust control of a human brain-machine interface
IEEE Trans on Biomedical Engineering | A dynamic ensemble Bayesian filter (DyEnsemble) is proposed to improve the robustness of online brain-machine interface (BMI) control by adaptively combining multiple neural decoding models to handle neural signal variability, showing significantly better accuracy and stability than conventional methods.
Jun 13, 2022