Ho Wei How, Abd Kadir Mahamad, Sharifah Saon, Maisara Othman, Herdawatie Abdul Kadir, Hakkun Elmunsyah
Drunk driving is one of the leading causes of traffic accidents in the world. In this work, the Development of Drowsiness and Drunk Driving Detection using YOLOv8 is designed to detect and alert the driver of a motorcar if the driver is intoxicated or sleepy. The project was developed to detect drowsiness and to send notifications by using Gmail. The proposed system uses machine learning which is YOLOv8 algorithms to detect drowsiness and drunk. It uses a simple mail transfer protocol to send email once drowsiness is detected. When developing the prototype, 3 main objectives are determined which are to develop a prototype for drowsiness detection, to develop a notification system for the prototype, and to analyze the performance of the prototype. The prototype employs a camera module to monitor the driver's eyes, determining whether they exhibit signs of drowsiness. Upon detecting drowsiness, the system activates a voice command, audibly instructing the driver to 'WAKE UP' through the system's speaker. Simultaneously, a notification is sent to a designated email address, informing recipients that the driver may not be in a suitable condition to operate a motor vehicle. The device utilizes Wi-Fi for seamless email notifications. During the prototype development phase, rigorous testing is conducted using two different individuals-one male and one female-to ensure the system's effectiveness in detecting both drowsiness and drunk. The testing results affirm that the developed prototype successfully detects drowsiness and drunk, triggering timely notifications through Gmail. This innovative solution holds promise in mitigating the risks associated with impaired driving, contributing to enhanced road safety. © 2024 IEEE.
Universiti Tun Hussein Onn Malaysia, Faculty of Electrical and Electronic Engineering, Johor, Batu Pahat, Malaysia; Universitas Negeri Malang, Jalan, Semarang, Indonesia
