The escalating challenges of urban traffic congestion necessitate the development of advanced traffic management systems. This paper introduces a novel approach combining vehicular fog computing with feature selection and deep learning techniques to enhance real-time traffic management in urban environments. Employing Particle Swarm Optimization (PSO) for feature selection and Long Short-Term Memory (LSTM) networks for traffic pattern analysis, the study aims to reduce latency in traffic data processing, improve congestion prediction accuracy, and optimize route management. The expected outcomes demonstrate the potential for significant advancements over existing traffic management solutions, offering a promising direction for future research and practical applications in intelligent transportation systems.
Real-Time Traffic Management Using Feature Selection and Deep Learning in Vehicular Fog Computing
Lect. Notes in Networks, Syst.
International Symposium on Intelligent Computing and Networking ; 2024 ; San Juan, USA March 18, 2024 - March 20, 2024
Proceedings of the International Symposium on Intelligent Computing and Networking 2024 ; Chapter : 26 ; 357-364
2024-08-08
8 pages
Article/Chapter (Book)
Electronic Resource
English
Predicting real-time traffic conflicts using deep learning
Elsevier | 2019
|Taylor & Francis Verlag | 2023
|