Researchers have developed a novel approach to model the human motor cortex during a brain-computer interface (BCI) task by treating it as a port-Hamiltonian system. This model incorporates gyroscopic coupling between neural phasors and a power-law energy decay driven by a Graph Neural Network (GNN) surrogate. The system was trained on real EEG data, achieving a low test Mean Squared Error and demonstrating scale-free criticality through metrics like a branching ratio near one, a 1/f power-law spectrum, and long-range correlations. The developed model can generate neuromodulation signals that restore phase-locking in silico, suggesting potential for structure-preserving BCI decoders. AI
IMPACT This research offers a new framework for understanding and potentially decoding brain signals, which could advance BCI technology.
RANK_REASON The cluster contains an academic paper detailing a new modeling approach for brain dynamics. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
