Research based on EEG for addiction level assessment methods and parietal/occipital lobes brain function analysis.

Abstract

The methamphetamine use disorder (MUD) has emerged as a global public health concern. This article proposes an assessment method that combines electroencephalography (EEG)-based deep learning, visualization and time domain and frequency domain analysis, aiming to ensure accuracy while identifying corresponding brain channels and improving assessment efficiency. The collected EEG data were classified correctly using a enhanced compact convolutional neural network, namely ECCN-Net. The classification results were validated using time domain and frequency domain analysis and Class Activation Mapping (CAM) visualization. The accuracy of the PO3 channel is the highest, reaching 85.15%. It is also discovered that MUD individuals have relatively higher relative power in the delta band.