Driver Fatigue Detection Using TGAM EEG Signal Processing Module

Driver fatigue and drunk driving are the leading causes of car accidents. To reduce car accidents, researchers suggest using Internet of Things (IoT) technology to detect in-vehicle air quality and alcohol-impaired effects that lead to driving fatigue and driving drunk. Consequently, in this study, we developed an IoT driver fatigue system based on a ThinkGear ASIC Module (TGAM) for capturing the driver’s electroencephalogram (EEG) signals. Additionally, the developed IoT system deployed SGP30 to detect in-vehicle carbon dioxide $\left(\mathrm{CO}_{2}\right)$ and PMS5003 to measure PM10 concentration. Furthermore, we deployed an MQ3 sensor to monitor driver alcohol consumption. The real-time in-vehicle air quality data and EEG data are displayed on a Node-RED webpage. The proposed system for driver fatigue detection also included a Raspberry Pi model B with 8G of RAM.