Citation

Al-Selwi, Hatem Fahd and Abdul Aziz, Azlan and Abas, Fazly Salleh and Alias, Mohamad Yusoff and Jamian, Saifulnizan and Ab Aziz, Nor Azlina (2025) Hybrid Spatiotemporal Graph Convolutional Network Enhanced with GRU for Traffic Forecasting. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 9.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Vehicular traffic flow prediction is a critical component of Intelligent Transportation Systems (ITS), playing a major role in alleviating congestion and optimizing traffic management. Additionally, accurate traffic forecasts are essential for efficient resource allocation in vehicular communication networks. Recent advancements in deep learning have enabled the use of Graph Neural Networks (GNNs) for traffic prediction, effectively capturing the complex spatiotemporal dependencies in traffic flow. However, existing models still face challenges in achieving higher accuracy and efficiency. In this study, we propose a Hybrid Spatiotemporal Graph Convolutional Network with GRU to enhance traffic flow prediction. The integration of Gated Recurrent Units (GRU) improves temporal feature extraction, refining the model's ability to capture dynamic traffic patterns over time. The proposed model is evaluated on multiple real-world traffic datasets to assess its predictive performance and computational efficiency. Experimental results show that our model achieves an average improvement of 6% over baseline models. Comparative analysis further highlights its superior performance, making it a valuable contribution to ITS development and traffic prediction research.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Deep learning, graph neural network,
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 08:20
Last Modified:	19 Mar 2026 02:15
URII:	http://shdl.mmu.edu.my/id/eprint/15589

Downloads

Edit (login required)