Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 1, 2025IET Intelligent Transport SystemsOpen Access

Traffic Flow Prediction Model Based on Transformer and Dynamic Graph Convolutional Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

PLPeiyu LiZTZhao TianCSChong Shang

Discussion

Loading...

Member takes

Overview

The proposed model improves prediction accuracy for traffic congestion in urban areas, suggesting enhanced management of spatiotemporal features.

Key Points

  • Prediction accuracy improves for traffic congestion, reducing MAE and RMSE by an average of 12.9% and 5.2%.
  • The model analyzes spatiotemporal features over multiple time horizons using highway datasets.
  • Analysis employs a Transformer-based architecture for capturing temporal dependencies and dynamic features.
  • Enhancements may enable better control and management strategies in intelligent transportation systems.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/69255737c0ce034ddc35af78https://doi.org/10.1049/itr2.70111
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Traffic flow prediction via dynamic hypergraph learning.2026
  2. 2Traffic Flow Prediction Based on Transformer And Multi-Graph Fusion Convolution2024 · 1 citations
  3. 3A Multi-Level Dynamic GCN-Transformer Framework with Spatio-Temporal Interaction for Traffic Flow Prediction2026
  4. 4A Freeway Traffic Flow Prediction Model Based on a Generalized Dynamic Spatio-Temporal Graph Convolutional Network2024 · 22 citations
  5. 5STGFormer: Spatio-Temporal Graph Transformer for Traffic Flow Prediction in Sparse-Sensing Scenarios2026