.png){kind=icon}
.png){kind=icon}
Return
Self-Supervised Pre-Training for EEG denoising
.png){kind=icon}
PRE
AI
DOI：10.1016/j.aei.2026.104662.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Knowledge-Driven self-supervised learning is proposed for EEG artifact removal. • The strategy consistently boosts state-of-the-art EEG denoising models. • Validated on public datasets with diverse artifacts and 5.32%–27.94% SNR gains.
Keywords:
EEG denoising
self-supervised learning
artifact removal
knowledge-driven
signal-to-noise ratio
Journal
IF:
9.9
Papers:
4.0K
Citations:
1.7W