Aureli Soria‐Frisch

The paper uses resting-state EEG and machine learning to stratify responses to tDCS in healthy children, identifying electrophysiological profiles linked to positive or negative responses.

This paper uses deep learning models on EEG spectrograms to diagnose and predict progression of REM Behavior Disorder, finding high accuracy in distinguishing patients who later develop Parkinson's or DLB from healthy controls.

The paper identifies beta-gamma phase-amplitude coupling deficits in ADHD children using EEG data during resting eyes closed state.

The paper uses EEG algorithmic complexity metrics to predict neurodegeneration in idiopathic RBD, finding decreased complexity correlates with poor prognosis.

This study identifies a non-stationary ADHD biomarker using Echo State Networks to analyze EEG differences between low and normal arousal states.

This paper introduces an Echo State Networks (ESN) approach for dynamical SSVEP detection in BCI systems, showing higher information transfer rates and shorter observation times compared to canonical correlation analysis.

This study investigates how tACS bursts at different frequencies affect neural oscillations and behavior during a visual task, finding frequency-specific changes in oscillation power, coherence, and complexity metrics.