An advanced approach for predicting driver drowsiness Using CNN and real-time facial detection

Driver sleepiness is a significant contributor to several traffic accidents, posing a threat to roadway safety. Eye Aspect Ratio (EAR), which observes eye movements to identify fatigue. The technology persistently monitors the facial features of a driver during eye closure and signals tiredness.. The device provides notifications to drivers via aural signals or vibrations, prompting them to take a break or sustain concentration. Data is broadcast by. The IoT-enabled cloud connection aggregates and analyzes historical data to discern patterns of drowsiness and enhance safety protocols. Fatalities and injuries caused by drowsy drivers amount to thousands every year, making it a major threat to road safety on a global scale. Even while DDD systems have come a long way, many of the current approaches still have drawbacks such being too obtrusive or having too long of a reaction time. To fill these shortcomings, this team developed a real-time, non-intrusive DDD system using face analysis and cutting-edge machine learning techniques. The unique thing about this study is that it uses three public datasets that are very important for studies on drowsiness detection—the NTHUDDD, YawDD, and UTA-RLDD—to systematically evaluate), and convolutional neural networks (CNNs).