Brain Wave Recognition Method for Depression in College Students Based on 2D Convolutional Neural Network

Baiyang Wang, Hongyan Fan, Meng Li, Fuchun Zhang, Yuelong Ji

Abstract: Depression is an imperceptible mental disease. Most patients who have symptoms of depression do not know that they have suffered from depression. College is a special stage of the formation of one's outlook on life, world outlook and values. College students face the pressure of life, study and employment,thus they are more likely to face the threat of depression. So how to quickly, efficiently and conveniently diagnose the degree of depression of college students is an urgent problem to be solved in college student management. Aiming at this problem, this paper proposes a neural network based on two-dimensional convolution depression EEG(Electroencephalogram) identification method. Using the EEG signals collected by only three electrodes, it can do a preliminary diagnosis of the degree of the depression patients, and it has solved the problem of specialized equipment and complicated diagnosis of traditional diagnosis of depression. First, brain electrical signal of different degrees of depression patients are collected ; Secondly, the collected signals are converted into two-dimensional images and then are input into the convolutional neural network for training; Finally, the trained model is loaded into the detection device, and the input EEG signals are diagnosized and classified. The results show that the proposed method can effectively classify EEG signals, and the accuracy can reach 98.6%. At the same time, the equipment cost is small, which is conducive to the wide application of the detection system.