DSTGN-ExpertNet: A Deep Spatio-Temporal Graph Neural Network for High-Precision Traffic Forecasting
Journal Title: Mechatronics and Intelligent Transportation Systems - Year 2025, Vol 4, Issue 1
Abstract
Accurate traffic prediction is essential for optimizing urban mobility and mitigating congestion. Traditional deep learning models, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), struggle to capture complex spatiotemporal dependencies and dynamic traffic variations across urban networks. To address these challenges, this study introduces DSTGN-ExpertNet, a novel Deep Spatio-Temporal Graph Neural Network (DSTGNN) framework that integrates Graph Neural Networks (GNNs) for spatial modeling and advanced deep learning techniques for temporal dynamics. The framework employs a Mixture of Experts (MoE) approach, where specialized expert models are dynamically assigned to distinct traffic patterns through a gating network, optimizing both prediction accuracy and interpretability. The proposed model is evaluated on large-scale real-world traffic datasets from Beijing and New York, demonstrating superior performance over conventional methods, including Spatio-Temporal Graph Convolutional Networks (ST-GCN) and attention-based models. With a mean absolute error (MAE) of 1.97 on the BikeNYC dataset and 9.70 on the TaxiBJ dataset, DSTGN-ExpertNet achieves state-of-the-art accuracy. These findings highlight the potential of GNN-based frameworks in revolutionizing traffic forecasting and intelligent transportation systems (ITS).
Authors and Affiliations
Seyyed Ahmad Edalatpanah, Javad Pourqasem
Keywords
Related Articles
- EP ID EP764544
- DOI https://doi.org/10.56578/mits040103
- Views 25
- Downloads 0
Enhancing Cold Chain Logistics: A Framework for Advanced Temperature Monitoring in Transportation and Storage
In the face of the increasingly demanding of goods transportation and storage, the orchestration of cold chain logistics emerges as a critical and multifaceted endeavor. This study, addressing a notable gap in literature...
Automated Vehicle Dent Detection Using Hybrid Image Processing and Fuzzy Decision Making
Automated detection of vehicle dents remains a challenging task due to variability in lighting conditions, surface textures, and the presence of minor deformations that may mimic actual dents. This paper presents a novel...
Simulation Analysis of Track Irregularity in High-Speed Maglev Systems Based on Universal Mechanism Software
As high-speed magnetic levitation (Maglev) technology continues to advance, the safety, stability, and passenger comfort of high-speed Maglev trains during operation are subject to increasingly stringent requirements. In...
Optimized Collaborative Scheduling of Unmanned Aerial Vehicles for Emergency Material Distribution in Flood Disaster Management
The effective allocation of emergency supplies is crucial in the aftermath of flood disasters, as it directly impacts response times and mitigates casualties and property losses. Traditional methods of material distribut...
Optimizing Vehicle Collision Safety: A Two-Mass Model with Dual Springs and Dampers for Accurate Crash Dynamics Prediction
A comprehensive analysis of vehicle collision dynamics is presented using a two-mass model that simulates the impact of a vehicle against a rigid barrier. The model incorporates dual springs and dampers to examine the in...