A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study

Excerpt

arXiv:2608.02083v2 Announce Type: replace Abstract: Closed-loop lower-limb exoskeleton control via Electroencephalography (EEG) remains limited by motion artifacts, low signal-to-noise ratio, and binary gait formulations that fail to capture full cortical gait complexity. We propose a 2-block Brain-Computer Interface (BCI) architecture: a trainable session-specific Feature Extraction Block with real-time artifact suppression and multi-domain feature extraction, coupled with a Decoder Block built