HYBRID MODEL FOR ROUTING SOLUTION IN UYO METROPOLIS USINGXGBOOST AND ANT COLONY OPTIMIZATION (ACO)

Abstract

The challenge of traffic congestion in rapidly urbanizing cities like Uyo Metropolis, Nigeria, necessitates innovative and intelligent routing solutions. Traditional GPS systems and static routing algorithms often fall short due to their inability to respond to real-time traffic fluctuations and unstructured road networks. This study proposes a hybrid model integrating eXtreme Gradient Boosting (XGBoost) for accurate traffic prediction with Ant Colony Optimization (ACO) for dynamic and intelligent route selection. The hybrid model leverages historical traffic data, demographic trends, and GPS logs to generate optimized paths that reduce congestion and travel time. Data were collected from key arterial roads in Uyo and analyzed using simulation tools. The findings reveal that the hybrid model outperforms conventional routing techniques in terms of adaptability, efficiency, and user satisfaction. The study underscores the potential of AI-driven models to revolutionize transport systems in developing urban centers and highlights key recommendations for policy, infrastructure, and further research.