An efficient full capacity traffic control management system using new bio-inspired algorithm-A University

Traffic congestion is a persistent and growing problem in many developed and developing countries. To effectively manage traffic flow, there is a need for a reliable and autonomous traffic control system. Traditional methods of traffic control, such as relying on traffic police or signals, have proven to be insufficient. Recent research suggests that machine learning models can be used to improve traffic control. This study proposes a bio-inspired traffic control system to address the various challenges of traffic management, such as traffic flow, speed limits, intersection signals, noise pollution, and environmental impacts. The proposed approach utilizes pre-trained models to detect, identify, and recognize vehicles and uses bio-inspired algorithms to optimize the control inputs based on an objective function. The system was simulated using the Blender tool with a GIS plugin, and the results were analyzed. The results show that the proposed system improved traffic flow by 28%, reduced the number of accidents by 37%, and successfully tracked 86% of the vehicles within the campus.