EEG-to-Gait Decoding via Phase-Aware Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fu, Xi, Jiang, Weibang, Liu, Rui, Müller-Putz, Gernot R., Guan, Cuntai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915794497044480
author Fu, Xi
Jiang, Weibang
Liu, Rui
Müller-Putz, Gernot R.
Guan, Cuntai
author_facet Fu, Xi
Jiang, Weibang
Liu, Rui
Müller-Putz, Gernot R.
Guan, Cuntai
contents Accurate decoding of lower-limb motion from EEG signals is essential for advancing brain-computer interface (BCI) applications in movement intent recognition and control. This study presents NeuroDyGait, a two-stage, phase-aware EEG-to-gait decoding framework that explicitly models temporal continuity and domain relationships. To address challenges of causal, phase-consistent prediction and cross-subject variability, Stage I learns semantically aligned EEG-motion embeddings via relative contrastive learning with a cross-attention-based metric, while Stage II performs domain relation-aware decoding through dynamic fusion of session-specific heads. Comprehensive experiments on two benchmark datasets (GED and FMD) show substantial gains over baselines, including a recent 2025 model EEG2GAIT. The framework generalizes to unseen subjects and maintains inference latency below 5 ms per window, satisfying real-time BCI requirements. Visualization of learned attention and phase-specific cortical saliency maps further reveals interpretable neural correlates of gait phases. Future extensions will target rehabilitation populations and multimodal integration.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22488
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EEG-to-Gait Decoding via Phase-Aware Representation Learning
Fu, Xi
Jiang, Weibang
Liu, Rui
Müller-Putz, Gernot R.
Guan, Cuntai
Signal Processing
Machine Learning
Accurate decoding of lower-limb motion from EEG signals is essential for advancing brain-computer interface (BCI) applications in movement intent recognition and control. This study presents NeuroDyGait, a two-stage, phase-aware EEG-to-gait decoding framework that explicitly models temporal continuity and domain relationships. To address challenges of causal, phase-consistent prediction and cross-subject variability, Stage I learns semantically aligned EEG-motion embeddings via relative contrastive learning with a cross-attention-based metric, while Stage II performs domain relation-aware decoding through dynamic fusion of session-specific heads. Comprehensive experiments on two benchmark datasets (GED and FMD) show substantial gains over baselines, including a recent 2025 model EEG2GAIT. The framework generalizes to unseen subjects and maintains inference latency below 5 ms per window, satisfying real-time BCI requirements. Visualization of learned attention and phase-specific cortical saliency maps further reveals interpretable neural correlates of gait phases. Future extensions will target rehabilitation populations and multimodal integration.
title EEG-to-Gait Decoding via Phase-Aware Representation Learning
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2506.22488