Transportation is integral to our daily lives, significantly easing various tasks. Unfortunately, recent years have witnessed an increase in tragic traffic accidents due to factors such as driver fatigue, distractions, and speed limit violations, leading to unfortunate fatalities. Drowsiness, short naps, gas leakage detection and alcohol consumption contribute to driver inattention, necessitating early warning systems. In this project, we've developed a prototype utilizing a Node MCU, a Pi Camera, and sensors to actively monitor drivers' eye movements, detect yawning, identify harmful chemicals, and detect alcohol consumption. Our primary goal is accident prevention and enhancing driver safety. Within the vehicle, an Internet of Things (IoT) and machine learning system transmit real-time data about the driver's behavior and driving patterns to the cloud for swift responses during emergencies, potentially saving lives. To maintain driver focus and prevent distractions, an integrated sound system alerts the driver when necessary. Cloud computing and machine learning recognize signs of driver fatigue based on data collected and stored in cloud services. Experimental testing of this device demonstrates its efficiency and effectiveness in enhancing road safety.
Prevention of Road Accidents Using Hybrid Machine Learning Algorithm
2024-03-14
700332 byte
Conference paper
Electronic Resource
English
Engineering Index Backfile | 1939
Predicting Road Accidents Using Machine Learning Models
IEEE | 2024
|Road accidents: Causes and prevention
Engineering Index Backfile | 1945
|