EEG-based characterization of auditory attention and meditation: an ERP and machine learning approach
Frontiers in Human Neuroscience August 26, 2025 Eyad Talal Attar 8 citations
Meditation alters brain responses to sound, increasing attention-related P300 amplitude and frontal alpha/beta power while reducing central theta power, indicating reduced cognitive load and enhanced internal focus. Greater meditation experience correlates with higher frontal alpha power. A machine learning classifier distinguished meditative from cognitive states with 86.7% accuracy, using P300 amplitude and frontal alpha and beta power as key predictors. These findings suggest EEG-based neurofeedback and brain–computer interfaces could monitor cognitive and emotional states in real time, supporting mental health applications.