EEG-Classification

This study aims to develop ML and DL methods which uses signals collected from electroencephalogram in application for detection of depression. We have extracted eleven statistical features form signal before feeding them to the model. We build three classifiers: Logistic Regression, Support Vector Machine, and 1-D Convolutional neural network. Our methods are tested of a dataset which comprise of signals form 30 healthy subjects and 34 MDD patients, these signals were collected from three different criteria: EC when eyes of subject are closed, EO when eyes of subject are open, and TASK when subject is doing some tasks. All three classifiers are applied on each of three types of signals, which gives a total of nine (3X3) experiments. Our results found that TASK signals given better accuracies of 88.4%, 89.3%, 90.21% for logistic regression, SVM and 1-D CNN respectively when compare to EC and EO signals, and also our results gave better accuracy than some of the available state-of-the-art methods