Traffic Forecasting Based on Integration of Adaptive Subgraph Reformulation and Spatio-Temporal Deep Learning Model
Open Access
- 9 March 2022
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 11 (6) , 861
Abstract
Traffic forecasting provides the foundational guidance for many typical applications in the smart city management, such as urban traffic control, congestion avoidance, and navigation guidance. Many researchers have focused on the spatio-temporal correlations under fixed topology structure in traffic network to improve the traffic forecasting accuracy. Despite their advantages, the existing approaches are not completely discussed that the association relationship among traffic network nodes are not invariable under different traffic conditions. In this paper, a novel traffic forecasting framework is proposed by integrating the dynamic association of traffic nodes with the spatio-temporal deep learning model. To be specific, an adaptive subgraph reformulation algorithm is designed first based on the specific forecasting interval to reduce the interference of irrelevant spatio-temporal information. After that, by enhancing the attention mechanism with the generative decoder, a spatio-temporal deep learning model with only one forward operation is proposed to avoid the degradation of accuracy in the long-term prediction, in which the spatio-temporal information and the external factors (such as weather and holiday) are fused together to be as an input vector. Based on the reformulated subgraph constructed of traffic nodes with closer spatio-temporal correlation, experiments show that the proposed framework consistently outperforms other GNN (Graph Neural Network)-based state-of-the-art baselines for various forecasting intervals on a real-world dataset.Keywords
Funding Information
- Natural Science Foundation of Shandong Province for Key Project (ZR2020KF006)
- National Natural Science Foundation of China (61903156, 61873324)
- University Innovation Team Project of Jinan (2019GXRC015)
This publication has 22 references indexed in Scilit:
- Geospatial data to images: A deep-learning framework for traffic forecastingTsinghua Science and Technology, 2019
- Structured Sequence Modeling with Graph Convolutional Recurrent Networks2018
- A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data2018
- Long short-term memory neural network for traffic speed prediction using remote microwave sensor dataTransportation Research Part C: Emerging Technologies, 2015
- A review of travel time estimation and forecasting for Advanced Traveller Information SystemsTransportmetrica A: Transport Science, 2014
- Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask LearningIEEE Transactions on Intelligent Transportation Systems, 2014
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- Object-based visual attention for computer visionArtificial Intelligence, 2003
- Optimal unsupervised learning in a single-layer linear feedforward neural networkNeural Networks, 1989
- Dynamic programming and the calculus of variationsJournal of Mathematical Analysis and Applications, 1960