Smart ADAS for EVs: A Deep Learning Approach to Driver Detection and Safety Enhancement

Electric Vehicle (EV) technology is an emerging field with several benefits, including lower running costs. Long-lasting batteries have always been the aim of EVs; thus, any additional hardware might significantly shorten battery life. Humans frequently make mistakes. As a result, driving habits like moderation and sports style may cause collisions and fatalities. Driver identification has emerged as a research hotspot in the fields of intelligent transportation and modern car development, and it is crucial to achieving personalized services for drivers and road traffic safety for electric vehicles. An enhanced deep learning-based method for identifying and supporting drivers in Better-performing electric vehicles was presented in this study. This method produces better results by utilizing a special real-world dataset that represents a variety of driving situations. ADAS is designed to increase vehicle efficiency and safety with features including autonomous braking, adaptive cruise control, and lane-keeping assistance. Thus, data-driven object recognition and localization methods are expected to be used in sophisticated driver assistance systems and self-driving automobiles. Specifically, deep neural networks demonstrated exceptional performance in object detection and classification from photos, frequently attaining superhuman levels of efficiency. The suggested ADAS model obtained 97.6% accuracy, 96.9% precision, 98.8% recall, and 99.3% sensitivity.