EEG-ReMinD: Enhancing Neurodegenerative EEG Decoding through Self-Supervised State Reconstruction-Primed Riemannian Dynamics

2025-01-14

AI Summary

Addressing key challenges in EEG decoding for neurodegenerative diseases—including data sparsity, substantial inter-subject variability, and heavy reliance on fine-grained annotations—this paper proposes a two-stage self-supervised framework. In the first stage, covariance matrices are modeled on the Riemannian manifold, and dynamic representation learning is guided by state reconstruction. In the second stage, attention mechanisms are integrated with Riemannian dynamical analysis to enable robust geometric temporal feature extraction without precise annotations. This work introduces, for the first time, a state-reconstruction-driven Riemannian dynamical modeling paradigm, substantially enhancing model generalization under noise and missing data. Evaluated on two neurodegenerative disease EEG datasets, the method achieves average classification accuracy improvements of 6.2% (full data) and 12.7% (noisy/missing data) over baseline methods.

Technology Category

• Machine Learning: Learning with Manifolds
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The development of EEG decoding algorithms confronts challenges such as data sparsity, subject variability, and the need for precise annotations, all of which are vital for advancing brain-computer interfaces and enhancing the diagnosis of diseases. To address these issues, we propose a novel two-stage approach named Self-Supervised State Reconstruction-Primed Riemannian Dynamics (EEG-ReMinD) , which mitigates reliance on supervised learning and integrates inherent geometric features. This approach efficiently handles EEG data corruptions and reduces the dependency on labels. EEG-ReMinD utilizes self-supervised and geometric learning techniques, along with an attention mechanism, to analyze the temporal dynamics of EEG features within the framework of Riemannian geometry, referred to as Riemannian dynamics. Comparative analyses on both intact and corrupted datasets from two different neurodegenerative disorders underscore the enhanced performance of EEG-ReMinD.

Problem

• EEG Decoding
• Brain-Computer Interface
• Neurodegenerative Diseases

Innovation

• EEG-ReMinD
• Self-supervised Learning
• Riemannian Dynamics