Urban traffic congestion emerges as a major challenge for transportation systems, adversely influencing both operational efficiency and the comprehensive quality of life. This chapter presents a method to predict congestion at intersections using advanced deep learning techniques. Using data from Vehicle Ad-Hoc Networks (VANET), this study focuses on understanding how various factors shape traffic patterns. These include weather, time of day, and special events. The process begins with collecting and cleaning data, setting the foundation for analysis. Several deep learning models are then employed to improve traffic predictions. A key feature of the approach is its integration with VANET systems. This enables real-time solutions like adjusting traffic lights, offering alternative routes, and sending alerts to drivers. The outcomes go beyond technical improvements, touching on broader benefits such as easing congestion and making roads safer. The work concludes by identifying areas where research could expand to refine smart traffic management further.
Smart Traffic Forecasting in Urban Junctions: A Deep Learning and VANET Approach
Studies Comp.Intelligence
2025-06-09
43 pages
Article/Chapter (Book)
Electronic Resource
English
VANET communication: A traffic flow approach
IEEE | 2012
|Deep Learning Mechanism for Region Based Urban Traffic Flow Forecasting
Springer Verlag | 2023
|