Empowering Safe Driving With Mobile Crowdsourced Drowsiness Detection

Abstract

The identification of sleepy driving has developed into a crucial study field since the automobile industry's rapid growth and growing worries about traffic safety. Driving while fatigued increases the risk of accidents and fatalities for both the driver and other road users. Our system's ability to use edge computing to do real-time sleepiness detection right on drivers' mobile devices is its primary feature. The suggested method accurately predicts the driver's level of awareness using a combination of sensor data, including facial expression analysis, eye movement tracking, and patterns of steering behavior. We use machine learning techniques to create are liable model that can tell the variation between alert and sleepy states. Our clever edge-based monitoring of driver attention system provides a potential answer for real-time and privacy-conscious driver alertness monitoring. By utilizing mobile crowdsourcing, we can build a sizable dataset that is constantly increasing, which will help us improve the precision of our model. The utilization of edge computing in this situation is a huge development in the field of traffic safety technology, with the potential to prevent countless accidents and save countless lives.