Analyze EEG and IMU Signals Base on Machine Learning to Predict Patients with Possible Depression

In this paper, we build data collection solutions to analyze and predict symtoms of depression. It uses EEG and IMU signals combined with Support Vector Machine (SVM) algorithm to evaluate the level of activity of the body and brain to collect signs that can cause depression, thereby taking preventive measures. We inherite from the OpenBCI platform and improve the hardware to increase the speed of data processing and transmission. Base on that, we combine with AI algorithm to improve the accuracy of depression predictions by more than 95% compared to other researchers.