A Convolutional Neural Network-Based Method for Real- Time Eye State Identification in Driver Drowsiness Detection

The use of Convolutional Neural Networks (CNNs) for drowsiness detection is an AI-based method for detecting and warning of human drowsiness or weariness. Deep learning models like convolutional neural networks (CNNs) learn by analysing images or videos, often focusing on human faces or eyes. Drowsiness cues may be recognised by these models, including drooping eyelids, yawning, and altered facial expressions. CNN-based sleepiness detection may be used to generate alarms or cautions using economic resources in real-time applications, such as driver monitoring systems, to help avoid accidents and improve safety. Artificial intelligence and computer vision access are at the heart of this technology, which aims to alleviate major safety risks associated with sleepiness and exhaustion. In this research, drowsiness detection and classification are accomplished with the help of a Sequential Convolutional Neural Network (CNN) model. The graphics processing unit (GPU) is used for producing preliminary data processing. The Deep Learning model is then shown graphically by analysing the Loss and Accuracy curves. With a predicted accuracy of 96%, the suggested model would pave the way for more research into sleepiness detection and categorization.