2024
Liu, Yutian; Rasouli, Soora; Wong, Melvin; Feng, Tao; Huang, Tianjin
RT-GCN: Gaussian-based spatiotemporal graph convolutional network for robust traffic prediction Journal Article
In: Information Fusion, vol. 102, pp. 102078, 2024, ISSN: 1566-2535.
Abstract | Links | BibTeX | Tags: Gaussian distribution, Graph convolutional network, Missing data, Robustness, Traffic prediction
@article{LIU2024102078,
title = {RT-GCN: Gaussian-based spatiotemporal graph convolutional network for robust traffic prediction},
author = {Yutian Liu and Soora Rasouli and Melvin Wong and Tao Feng and Tianjin Huang},
url = {https://www.sciencedirect.com/science/article/pii/S1566253523003949},
doi = {https://doi.org/10.1016/j.inffus.2023.102078},
issn = {1566-2535},
year = {2024},
date = {2024-01-01},
journal = {Information Fusion},
volume = {102},
pages = {102078},
abstract = {Traffic forecasting plays a critical role in intelligent transportation systems (ITS) in smart cities. Travelers as well as urban managers rely on reliable traffic information to make their decisions for route choice and traffic management. However, noisy or missing traffic data poses a problem for accurate and robust traffic forecasting. While data-driven models such as deep neural networks can achieve high prediction accuracy with complete datasets, sensor malfunctions, and environmental effects degrade the performance of such models, as these models rely heavily on precise traffic measurements for model training and estimation. Consequently, incomplete traffic data poses a challenge for robust model design that can make accurate traffic forecasts with noisy/missing data. This research proposes the Robust Spatiotemporal Graph Convolutional Network (RT-GCN), a traffic prediction model that handles noise perturbations and missing data using a Gaussian distributed node representation and a variance based attention mechanism. Through experiments conducted on four real-world traffic datasets using diverse noisy and missing scenarios, the proposed RT-GCN model has demonstrated its ability to handle noise perturbations and missing values and provide high accuracy prediction.},
keywords = {Gaussian distribution, Graph convolutional network, Missing data, Robustness, Traffic prediction},
pubstate = {published},
tppubtype = {article}
}
Traffic forecasting plays a critical role in intelligent transportation systems (ITS) in smart cities. Travelers as well as urban managers rely on reliable traffic information to make their decisions for route choice and traffic management. However, noisy or missing traffic data poses a problem for accurate and robust traffic forecasting. While data-driven models such as deep neural networks can achieve high prediction accuracy with complete datasets, sensor malfunctions, and environmental effects degrade the performance of such models, as these models rely heavily on precise traffic measurements for model training and estimation. Consequently, incomplete traffic data poses a challenge for robust model design that can make accurate traffic forecasts with noisy/missing data. This research proposes the Robust Spatiotemporal Graph Convolutional Network (RT-GCN), a traffic prediction model that handles noise perturbations and missing data using a Gaussian distributed node representation and a variance based attention mechanism. Through experiments conducted on four real-world traffic datasets using diverse noisy and missing scenarios, the proposed RT-GCN model has demonstrated its ability to handle noise perturbations and missing values and provide high accuracy prediction.