Intelligent traffic control system leveraging on an efficient nature-inspired algorithm

Abstract

With the increasing number of road vehicles, traffic congestion has become a significant issue in many countries. This problem is particularly acute in developing countries like Ghana, where the traffic management system is considered obsolete and unable to handle the growing number of cars. Inefficient traffic systems can lead to delays and even situations where individuals may lose their lives. To tackle this issue, our research paper proposes the development of an intelligent traffic control system that uses identified nature-occurring algorithms and a machine learning model; Yolov5. The research aims to investigate how these algorithms can be used to improve the status quo of the Ghanaian traffic control system and provide optimal solutions for traffic control systems. This research will also examine how insights from transportation analytics can enhance the commuter experience. The research questions to be addressed include: How can efficient nature-inspired algorithms improve the Ghanaian traffic control system? and Will insights from transportation analytics readily enhance the commuter experience? By answering these research questions, the study will provide valuable insights into the development of intelligent traffic management systems tailored to Ghanaian commuters' specific needs. This, in turn, could lead to more efficient traffic flow, reduced road accidents, and improved productivity, which are crucial for the country's sustainable economic growth. Upon generating optimal fitness values, this research's findings can be used to identify which direction at a traffic intersection has the lowest average waiting time.