A customized deep learning approach to integrate network-scale online traffic data imputation and prediction. (November 2021)

• Record Type: Journal Article
• Authors: Zhang, Zhengchao; Lin, Xi; Li, Meng; Wang, Yinhai
• Is Part Of: Transportation research. Volume 132(2021)
• Publication Date: 2021-11
• Subjects: Traffic prediction -- Online data imputation -- Deep learning -- Bidirectional recurrent neural network -- Graph convolution -- 1 × 1 Convolution; Transportation -- Periodicals; Transportation -- Technological innovations -- Periodicals; 388.011
• DOI: 10.1016/j.trc.2021.103372
• Languages: English
• ISSNs: 0968-090X

Abstract

Highlights: Integrate network-scale online traffic data imputation and prediction. A customized bidirectional recurrent neural network with designed imputation mechanism. Innovative hidden unit incorporates graph convolution and 1 × 1 convolution. Both real-world traffic speed and flow datasets to evaluate model performances. Abstract: Online data imputation and traffic prediction based on real-time data streams are essential for the intelligent transportation systems, particularly online navigation applications based on the real-time traffic information. However, the inevitable data missing problem caused by various disturbances undermines the information contained in such real-time data, thereby threatening the reliability of data acquisition as well as the prediction results. Such scenarios raise a strong need for integrating the tasks of network-scale online data imputation and traffic prediction, because the existing two-step approaches that separate the above procedures cannot be implemented in an online manner. In this paper, we propose a customized spatiotemporal deep learning architecture, named the graph convolutional bidirectional recurrent neural network (GCBRNN), to combine network-scale online data imputation and traffic prediction into an integrated task. The imputation mechanism and bidirectional framework are developed to cooperatively estimate missing entries and infer future values. We further design a network-scale graph convolutional gated recurrent unit (NGC-GRU) within the GCBRNN, which applies the graph convolution operation and 1 × 1 convolution module to capture the spatiotemporal dependencies in the traffic data. Experiments are carried out on two real-world traffic networks, including traffic speed and flow datasets. The comparison results demonstrate that our approach significantly outperforms several classical benchmark models with respect to both the imputation and prediction tasks on two datasets under various missing data rates.