An Efficient Drowsiness Detection and Driver Alert System using OCNN

To analyze traffic accident data and identify priority enhancement junctions, this research aims to build a high accident risk prediction model. To identify possible high accident risk locations for traffic management departments to use in developing countermeasures to reduce accident risk, an intersection accident risk prediction model was created using a variety of mechanical learning approaches. the creation and examination of an accident record. The research work focus on identifying the drowsiness using EEG signal. It identified environmental factors at intersections that affect accident risk levels using optimized CNN. An accident risk prediction model was developed using optimized Convolutional Neural Network (CNN)-Heuristic. To build up a drowsiness identification framework that can recognize weariness in drivers to forestall mishaps and the ground truth drowsiness detection system that is depending on the vigorous left, focus and right-AOEs and fixed back AOE (Area of eye vision). Additionally, this model can identify the crucial elements that influence the likelihood of high-risk crossings, giving traffic management organizations a strong foundation for choosing an intersection. This could be used to forecast future risk levels and aid in the reduction of traffic accidents by using the same climatic variables as high-risk crossings as model inputs. It can serve as a model for upcoming improvements to junction architecture and the surrounding area.