EEG-based ADHD Classification using Multiresolution Analysis and Machine Learning on Frontal and Other Brain Regions

This study uses empirical mode decomposition and discrete wavelet transform for feature extraction from EEG data to classify ADHD versus control subjects using machine learning algorithms. The research investigates optimal electrode placement and identifies brain region groupings most effective for ADHD detection, with findings suggesting frontal/prefrontal regions are particularly relevant for classification accuracy.