Enhancing Intersection Traffic Safety utilizing V2I Communications: Design and Evaluation of Machine Learning based Framework

In recent years, improving intersection traffic safety has become a major focus for researchers. However, it remains significant concern due to the increasing number of vehicles and introduction autonomous cooperative driving systems. Advancements in artificial intelligence (AI) vehicle-to-everything (V2X) technologies offer promising solutions reduce collisions between vehicles. As V2X are slowly being integrated into systems, questions arise about their impact on effectiveness. This research area is relatively unexplored but potential enhance safety. this paper, we introduce Intersection Traffic Safety Framework (ITSF), safety-oriented system devised mitigate at road intersections. framework achieves through implementation collision avoidance mechanism that harnesses vehicle-to-infrastructure (V2I) communications. Additionally, incorporates machine learning model tasked with distinguishing posing risk those do not, as part process. Furthermore, work assesses performance by considering critical factors like penetration rate V2X-enabled vehicles, end-to-end latency, responsiveness drivers alerts. The proposed approach proves highly effective ensuring users’ 60% or higher, resulting reduction nearly 98% accuracy classifying risky algorithm successful even when some neglect warnings, showcasing its robustness minimizing rates.