Machine Learning and IoT Integration in Kigali Traffic
DOI:
https://doi.org/10.70619/vol5iss7pp24-43Keywords:
Traffic Management, Smart Cities, Urban Planning, Kigali, Artificial Intelligence, Congestion MitigationAbstract
This paper presents the development and implementation of Machine Learning and IoT Integration in Kigali designed to mitigate urban congestion in Kigali, Rwanda. The system integrates real-time traffic monitoring, adaptive signal control, and predictive analytics to optimize traffic flow across the city's major corridors. The research follows the Structured System Analysis and Design Method (SSADM) and employs machine learning algorithms for traffic pattern prediction. The paper details system architecture, sensor integration, real-time processing capabilities, and implementation results from pilot deployment across five major intersections in Kigali. The study concludes that the proposed Machine Learning and IoT Integration in Kigali reduces average travel time by 32% and decreases fuel consumption by 28%. Additionally, it discusses the potential impact of AI-driven solutions in optimizing urban mobility and reducing environmental impact.
References
Zhang R., A. Ishikawa, W. Wang, B. Striner, and O. K. Tonguz, "Intelligent traffic signal control: Using reinforcement learning with partial detection," IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 1, pp. 404-415, 2021.
Hoang L. T., S. Jung, C. H. Youn, and S. Lee, "Smart traffic management system using IoT and machine learning," Smart Cities, vol. 3, no. 4, pp. 1277-1291, 2020.
García-Torres M. A., C. Gómez-Vela, D. Ruiz-Aguilar, and J. C. Fernandez-Caballero, "Machine learning approaches for traffic flow prediction in smart cities," Sensors, vol. 21, no. 12, p. 4020, 2021.
Adebayo A. O., C. K. Ayo, and M. O. Adebiyi, "Traffic management system for developing countries: A case study of Lagos metropolis," International Journal of Modern Engineering Research, vol. 4, no. 8, pp. 12-20, 2019.
S. Wang, X. Zhang, and L. Yu, "Deep learning-based traffic flow prediction for intelligent transportation systems," IEEE Access, vol. 8, pp. 142562-142574, 2020.
Chen H., L. Zhang, D. Lo, C. Feng, H. Wen, and L. Noboa, "Real-time traffic flow prediction using machine learning methods," Computer Networks, vol. 178, p. 107345, 2020.
Abdelghany K. M., H. S. Mahmassani, and A. Chiu, "Spatial microassignment of travel demand with activity/trip chains," Transportation Research Record, vol. 1831, no. 1, pp. 61-71, 2019.
Duan Y., Y. Lv, W. Kang, Z. Li, and F. Y. Wang, "Traffic flow prediction with big data: A deep learning approach," IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 2, pp. 865-873, 2018.
Rwanda Development Board, "Smart City Master Plan for Kigali," Ministry of Infrastructure, Kigali, Rwanda, Technical Report RDB-2022-001, 2022.
East African Community, "Regional Traffic Management Guidelines," EAC Secretariat, Arusha, Tanzania, Policy Document EAC-TM-2021, 2021.
Sun B., L. Zhang, and M. Wang, “A resilience-oriented traffic signal control system under flood scenarios,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 2, pp. 1452–1465, 2022.
Zhu L., X. Chen, and J. Wu, “Design and evaluation of solar-powered traffic signal systems for sub-Saharan cities,” IEEE Access, vol. 8, pp. 88763–88774, 2020.
El-Fadel M. F. and A. Bou-Zeid, “Public-private partnerships in smart urban infrastructure: A systems perspective,” Journal of Infrastructure Systems, vol. 26, no. 1, pp. 04019040, 2020.
Alghamdi S., H. Alshareef, and I. Khan, “Preventive maintenance scheduling using IoT analytics in traffic control systems,” IEEE Internet of Things Journal, vol. 9, no. 5, pp. 3251–3261, 2022.
Rwanda Ministry of Infrastructure, Smart Mobility and Traffic Flow Analysis Report, Kigali, Technical Report MININFRA-2022-TF, 2022.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Bwiza Museruka Linda, Dr. KN Jonathan, Dr. Djuma Sumbiri
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
