Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 12, 2025Open Access

A Traffic Flow Forecasting Method Based on Transfer-Aware Spatio-Temporal Graph Attention Network

View Full Paper
Ask AI
Bookmark
Share

Authors

YZYan ZhouXWXiaodi WangJJJie Jia

Discussion

Loading...

Member takes

Overview

Observational analysis identifies improved traffic flow forecasting using spatio-temporal models, indicating enhanced urban traffic management.

Key Points

  • TAGAT-LSTM-trans improves traffic flow forecasting accuracy by addressing spatial dependencies without relying solely on road node connectivity.
  • Experiments demonstrate that TAGAT-LSTM-trans significantly outperforms baseline models in capturing spatio-temporal dynamics across datasets.
  • The proposed model utilizes a novel transfer probability matrix and a distance decay matrix to better represent node interactions.
  • Through integrating LSTM and a Transformer encoder, the model effectively manages temporal dependencies in traffic forecasting.

Cite This Study

Zhou et al. (2025) studied this question.

synapsesocial.com/papers/68ebabe3155248a327effdd7https://doi.org/10.20944/preprints202510.0636.v1
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. 1A Traffic Flow Forecasting Method Based on Transfer-Aware Spatio-Temporal Graph Attention Network2025
  2. 2A Traffic Flow Forecasting Method Based on Transfer-Aware Spatio-Temporal Graph Attention Network2025
  3. 3A Long Term Transformer-based Spatiotemporal Graph Attention Network for Traffic Flow Forecasting2025
  4. 4A Multilayer Spatiotemporal Correlation-Aware Graph Attention Network for Traffic Flow Prediction2025
  5. 5Memory-Augmented Spatio-Temporal Transformer for Robust Traffic Flow Forecasting2026 · 2 citations