Mahmoud Alipour

This paper develops a real-time sleep stage classifier for N2 and N3 sleep using scalp and intracranial EEG, showing high accuracy and informing stimulation timing.

This study shows thalamic stereo-EEG can detect sleep stages N2 and N3 with high accuracy, comparable to scalp EEG, using machine learning classifiers.

The paper identifies theta-band power as a predictor of slow oscillation (SO) initiation and spatial extent using EEG data from healthy adults.

The paper examines how different thalamic nuclei coordinate with cortical slow oscillations during sleep, finding nucleus-specific patterns linked to propagation types.

The paper investigates how slow oscillations gate interictal spikes across the thalamocortical-epileptogenic network in human epilepsy, finding region-specific coupling and predictive pre-onset phase-amplitude coupling.

This paper develops a predictive model for sleep slow oscillation (SO) occurrences during NREM sleep, enabling more precise targeting for brain stimulation by analyzing SO timing and decay patterns across sleep cycles.

This paper introduces a classification-based generative approach to optimize closed-loop tACS during sleep by targeting global slow oscillations, showing potential for improving memory consolidation.