OPTIMIZATION OF URBAN TRANSPORTATION SYSTEMS USING ARTIFICIAL INTELLIGENCE
Keywords:
Artificial Intelligence, Traffic Flow Optimization, Machine Learning, IoT, Edge Computing.Abstract
This article provides a comprehensive analysis of the possibilities for optimizing urban traffic flow and reducing congestion through the application of Machine Learning, Deep Learning, and Reinforcement Learning methods [1,3]. Within the scope of the study, the role of these approaches in traffic prediction, real-time management, and adaptive decision-making is examined in depth.
In addition, the paper explores the integration of Internet of Things (IoT) and Edge Computing technologies, focusing on mechanisms for real-time data collection, processing, and rapid analysis [5,9] of large-scale data. This approach enables the reduction of latency in transport infrastructure, supports decentralized management, and enhances overall system efficiency.
The study also analyzes practical applications such as intelligent traffic light systems, traffic flow prediction models, dynamic routing, and passenger flow management, evaluating their economic and environmental impacts.
In conclusion, the article outlines key directions for the development of urban transport management systems using artificial intelligence. In particular, it proposes practical and research-based recommendations aimed at advancing digital transformation, establishing sustainable transport systems, reducing CO₂ emissions, and creating a safer and more convenient urban mobility environment for city residents.
Downloads
References
1. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
2. Tampère, C. M., & Immers, L. H. (2007). Traditional vs. Intelligent Traffic Management
Systems. Journal of Transport Engineering.
3. Zhang, J., et al. (2023). A Comprehensive Review of Traffic Flow Prediction: Models
and Methods. IEEE Transactions on Intelligent Transportation Systems.
4. Bibri, S. E. (2018). The IoT and Big Data Analytics for Smart Sustainable Cities.
Sustainable Cities and Society.
5. Shi, W., et al. (2016). Edge Computing: Vision and Challenges. IEEE Internet of Things Journal.
6. Vaswani, A., et al. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems.
7. Zhu, L., et al. (2021). Cybersecurity in Intelligent Transportation Systems: A Survey. IEEE Communications Surveys & Tutorials.
8. Li, Y., & Gunji, V. (2024). Real-time Traffic Monitoring using IoT and Machine Learning. Journal of Real-Time Image Processing.
9. Satyanarayanan, M. (2017). The Emergence of Edge Computing. Computer.
10. Wang, X., et al. (2024). Deep Reinforcement Learning for Adaptive Traffic Signal. Control in Urban Networks. Engineering Applications of Artificial Intelligence.
