STGNN-FAM: A Traffic Flow Prediction Model for Spatiotemporal Graph Networks Based on Fusion of Attention Mechanisms

Network traffic state prediction has been constantly challenged by complex spatiotemporal features of traffic information as well as imperfection in streaming data. This paper proposes a traffic flow prediction model for spatiotemporal graph networks based on fusion of attention mechanisms (STGNN-FA...

Full description

Saved in:
Bibliographic Details
Published in:Journal of advanced transportation 2023-05, Vol.2023, p.1-19
Main Authors: Qi, Xueying, Hu, Weijian, Li, Baoshan, Han, Ke
Format: Article
Language:English
Subjects:
Accuracy
Benchmarks
Communications traffic
Data transmission
Deep learning
Feature extraction
Kalman filters
Machine learning
Methods
Neural networks
Prediction models
Queuing theory
Roads & highways
Sensors
Time series
Traffic flow
Traffic information
Traffic models
Traffic speed
Transportation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Network traffic state prediction has been constantly challenged by complex spatiotemporal features of traffic information as well as imperfection in streaming data. This paper proposes a traffic flow prediction model for spatiotemporal graph networks based on fusion of attention mechanisms (STGNN-FAM) to simultaneously tackle these challenges. This model contains a spatial feature extraction layer, a bidirectional temporal feature extraction layer, and an attention fusion layer, which not only fully considers the temporal and spatial features of the traffic flow problem but also uses the attention mechanism to enhance the critical temporal and spatial features to achieve more accurate and robust predictions. Experimental results on a network traffic speed dataset PeMSD7 show that the proposed STGNN-FAM outperforms several important benchmarks in prediction accuracy and the ability to withstand interference in the data stream, especially for mid- and long-term prediction of 30 minutes and 45 minutes.
ISSN:0197-6729
2042-3195
DOI:10.1155/2023/8880530