Management of road traffic and congestion is a critical feature of urban planning and infrastructure development. Traffic congestion has recently become a major problem on a global scale due to the rapid increase in industrialization and the number of vehicles on the road. Efficient traffic management not only enhances the flow of vehicles but also contributes to reducing fuel consumption, minimizing air pollution, and improving road safety. Traditional traffic management methods, which primarily rely on static models and historical data, have proven to be insufficient in handling the complexities of modern transportation systems. Therefore, there is a growing need for advanced techniques that can predict traffic patterns and optimize traffic flow in real time. Techniques of machine learning and deep learning have become increasingly effective in recent years for addressing the difficulties in controlling traffic and predictions. By influencing the vast amount of data generated from traffic sensors, GPS devices, and other sources, machine learning and deep learning algorithms can analyze, learn, and predict traffic conditions more accurately than traditional methods. These techniques are particularly effective in handling the dynamic and nonlinear nature of traffic flow, making them ideal for real-time applications in traffic control, congestion prediction, and incident management.
Review on Traffic Prediction Framework Using Machine and Deep Learning Algorithms
2025-03-19
1451953 byte
Conference paper
Electronic Resource
English
An Adaptive Framework for Traffic Congestion Prediction using Deep Learning
Bentham Science Publishers | 2024
|