Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface

2026-08-17

AI Summary

This study addresses the challenges of poor cross-day transferability and online decoding in motor imagery brain-computer interfaces (MI-BCI) by proposing the MRieHy framework. Integrating Riemannian geometry with dual hypergraph learning, this method employs covariance alignment and feature hypergraph-weighted fusion, combined with a sliding buffer mechanism to enable test-time adaptation and real-time distribution alignment. Extensive validation on ECoG and EEG datasets demonstrates that MRieHy significantly outperforms state-of-the-art methods, effectively enhancing both cross-session transfer performance and online recognition accuracy. These findings establish a novel paradigm for developing highly robust BCI systems capable of maintaining reliable performance across varying temporal conditions and non-stationary neural signals.

Abstract

In clinical motor imagery brain-computer interface (MI-BCI) decoding, cross-day transferability and online operation remain two critical challenges. Hypergraphs can improve transferability by capturing higher-order sample relationships, yet existing hypergraph-based methods for online emotion recognition neglect the cross-day benefits of Riemannian geometry widely adopted in EEG transfer learning. To bridge this gap, we propose the Multi-feature Riemannian Hypergraph (MRieHy), a framework tailored for online test-time adaptation in MI-BCI decoding that leverages Riemannian geometry to strengthen cross-day transferability. MRieHy first computes Riemannian means of covariance matrices from cross-day training data to align multi-day distributions. It then constructs a hypergraph over covariance matrices using Riemannian distance, complemented by a second hypergraph over deep features built with cosine similarity. The two hypergraphs are fused via adaptively learned combination weights, jointly optimized with the label projection matrices. During online testing, MRieHy maintains a first-in-first-out buffer of recent samples, performs Riemannian alignment on the buffered data, and decodes with the learned hypergraph. Extensive experiments on a private four-class ECoG dataset and two public four-class EEG datasets validate that MRieHy achieves notable performance gains over state-of-the-art baselines.

Problem

• Motor Imagery BCI
• Online Test-Time Adaptation
• Cross-day Transferability
• Riemannian Geometry
• Hypergraph

Innovation

• Riemannian Hypergraph
• Online Test-Time Adaptation
• Multi-Feature Fusion
• Cross-Day Transferability
• Motor Imagery BCI