Keywords:-
Article Content:-
Abstract
Traffic management systems are vital for modern cities, aiming to optimize vehicle and pedestrian flow, improve safety, and reduce congestion. Despite widespread deployment of traffic technologies, urban congestion remains a persistent issue due to rapid city expansion, population growth, and increased vehicle movement, causing economic costs and health hazards from pollution. This study developed an Intelligent Traffic Advisory Model (ITAM) using a fuzzy-graph neural network (FGNN) to recommend efficient routes and reduce signal-induced congestion. The fuzzy inference engine handled traffic uncertainties, while the graph-based engine modeled network nodes and edges. Candidate routes were evaluated using a multi-criteria framework, with Dijkstra’s algorithm as a baseline for shortest paths and A* for traffic-aware planning. The model was tested with simulations and real-world urban datasets, showing strong performance: commute times decreased by 18.4%, peak-hour throughput increased by 22.1%, and fuel efficiency improved by 12.9%. The ITAM offered real-time, adaptive route recommendations and a multi-stakeholder framework for traffic authorities and emergency services. IoT-enabled sensors, adaptive traffic lights, and live data integration were recommended to maintain and improve the FGNN model’s accuracy. This study contributes to intelligent traffic management by combining fuzzy logic and graph neural networks for adaptive, precise route recommendations. Simulation results showed 98.3% accuracy, demonstrating the model’s effectiveness and the advantage of a proactive, scalable, and modular traffic management approach over traditional reactive systems.
References:-
References
Alkhatib, F., Hassan, R., & Lee, C. (2022). Urban traffic control system with lane weight and vehicle priority for congestion reduction. Simulation Modelling Practice and Theory, 115, 102512. https://doi.org/10.1016/j.simpat.2021.102512
Chen, X., Li, H., & Zhang, Y. (2023). Intelligent traffic management systems: Integration of sensors, signals, and communication networks. Transportation Research Part C: Emerging Technologies, 145, 104728. https://doi.org/10.1016/j.trc.2023.104728
Duc, H., Nguyen, T., & Pham, K. (2023). Urban traffic congestion in developing cities: Causes and mitigation strategies. Journal of Urban Planning and Development, 149(3), 04023015. https://doi.org/10.1061/(ASCE)UP.1943-5444.0000845
Fattah, K., Bello, S., & Okonkwo, M. (2022). Economic losses due to urban traffic congestion in Nigerian cities: A case study of Lagos and Port Harcourt. Nigerian Journal of Transport and Logistics, 8(2), 22–35.
Guo, L., & Harmati, A. (2024). Lane-changing optimization in congested traffic using Deep Q-Learning with request–respond mechanism. Transportation Research Part C: Emerging Technologies, 161, 104898. https://doi.org/10.1016/j.trc.2024.104898
Khadra, A. (2023). V2X-based traffic management hardware system for real-time data collection. Journal of Intelligent Transportation Systems, 27(5), 567–581. https://doi.org/10.1080/15472450.2023.2101234
Khan, M., Ali, R., & Ahmed, S. (2022). IoT-based over-speed detection system using GSM, GPS, and Arduino. International Journal of Vehicular Technology, 2022, 4589213. https://doi.org/10.1155/2022/4589213
Li, J., Wang, P., & Zhao, Q. (2023). Predictive algorithms and machine learning in urban traffic management. Journal of Advanced Transportation, 2023, 987654. https://doi.org/10.1155/2023/987654
Lilhore, U., Gupta, P., & Singh, R. (2022). Adaptive traffic management system using IoT and DBSCAN clustering for accident detection. Journal of Transportation Safety & Security, 14(6), 1235–1250. https://doi.org/10.1080/19439962.2022.2104567
Olaniyi, A., & Emmanuel, T. (2024). Traffic congestion and productivity losses in Nigerian metropolitan cities. African Transport Review, 16(1), 101–118.
Ramesh, P., Kumar, S., & Sharma, A. (2022). Peer-to-peer trust management in VANET using Aumann’s agreement theorem. IEEE Transactions on Intelligent Transportation Systems, 23(8), 9874–9886. https://doi.org/10.1109/TITS.2022.3165487
Saleem, M., Ahmed, Z., & Malik, H. (2022). Fusion-based intelligent traffic congestion control system for vehicular networks. IEEE Access, 10, 87654–87667. https://doi.org/10.1109/ACCESS.2022.3198765
Suzuki, T., & Marumo, T. (2020). GLOSA: Green Light Optimal Speed Advisory system for enhanced intersection safety. Transportation Research Record, 2674(3), 112–124. https://doi.org/10.1177/0361198120912345
Bassey, A.T; Davies, I. N; and Abiodun, I. A (2025) presented a study titled Comparative Analysis of AI Techniques in a Traffic Advisory Model: GNN, FNN, and A* in the International Journal of Mathematics and Computer Research.: 5576-5581 https://doi.org/10.47191/ijmcr/v13i8.10