AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Communications in Transportation Research Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

AGNP: Network-wide short-term probabilistic traffic speed prediction and imputation

Meng Xua, Yining Dia, Hongxing Dinga, Zheng Zhub,c,d( ), Xiqun Chenb,c,d, Hai Yanga,e
Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong, China
Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, 310058, China
Zhejiang Provincial Engineering Research Center for Intelligent Transportation, Hangzhou, 310058, China
Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies, Hangzhou, 310058, China
Intelligent Transportation Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511458, China
Show Author Information

Abstract

The data-driven Intelligent Transportation System (ITS) provides great support to travel decisions and system management but inevitably encounters the issue of data missing in monitoring systems. Hence, network-wide traffic state prediction and imputation is critical to recognizing the system level state of a transportation network. Abundant research works have adopted various approaches for traffic prediction and imputation. However, previous methods ignore the reliability analysis of the predicted/imputed traffic information. Thus, this study originally proposes an attentive graph neural process (AGNP) method for network-level short-term traffic speed prediction and imputation, simultaneously considering reliability. Firstly, the Gaussian process (GP) is used to model the observed traffic speed state. Such a stochastic process is further learned by the proposed AGNP method, which is utilized for inferring the congestion state on the remaining unobserved road segments. Data from a transportation network in Anhui Province, China, is used to conduct three experiments with increasing missing data ratio for model testing. Based on comparisons against other machine learning models, the results show that the proposed AGNP model can impute traffic networks and predict traffic speed with high-level performance. With the probabilistic confidence provided by the AGNP, reliability analysis is conducted both numerically and visually to show that the predicted distributions are beneficial to guide traffic control strategies and travel plans.

Keywords

Graph neural networksPrediction and imputationNeural processesCongestion prediction

References

 

Bae, B., Kim, H., Lim, H., Liu, Y., Han, L.D., Freeze, P.B., 2018. Missing data imputation for traffic flow speed using spatio-temporal cokriging. Transport. Res. C Emerg. Technol. 88, 124–139.
Crossref Google Scholar
 

Candela, J.Q., Rasmussen, C.E., 2005. A unifying view of sparse approximate Gaussian process regression. J. Mach. Learn. Res. 6, 1939–1959.
Google Scholar
 

Chan, R.K.C., Lim, J.M.Y., Parthiban, R., 2021. A neural network approach for traffic prediction and routing with missing data imputation for intelligent transportation system. Expert Syst. Appl. 171, 114573.
Crossref Google Scholar
 

Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y., 2018. Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8 (1), 1–12.
Crossref Google Scholar
 

Chen, X., He, Z., Wang, J., 2018. Spatial-temporal traffic speed patterns discovery and incomplete data recovery via SVD-combined tensor decomposition. Transport. Res. C Emerg. Technol. 86, 59–77.
Crossref Google Scholar
 

Chen, X., He, Z., Chen, Y., Lu, Y., Wang, J., 2019. Missing traffic data imputation and pattern discovery with a Bayesian augmented tensor factorization model. Transport. Res. C Emerg. Technol. 104, 66–77.
Crossref Google Scholar
 
Chung, J., Gulcehre, C., Cho, K., Bengio, Y., 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Proceedings of Neural Information Processing Systems (NeurIPS).
 

Cui, Z., Henrickson, K., Ke, R., Wang, Y., 2019. Traffic graph convolutional recurrent neural network: a deep learning framework for network-scale traffic learning and forecasting. IEEE Trans. Intell. Transport. Syst. 21 (11), 4883–4894.
Crossref Google Scholar
 

Cui, Z., Lin, L., Pu, Z., Wang, Y., 2020. Graph Markov network for traffic forecasting with missing data. Transport. Res. C Emerg. Technol. 117, 102671.
Crossref Google Scholar
 

de Medrano, R., Aznarte, J.L., 2020. A spatio-temporal attention-based spot-forecasting framework for urban traffic prediction. Appl. Soft Comput. 96, 106615.
Crossref Google Scholar
 

Deb, S., Strawderman, L., Carruth, D.W., DuBien, J., Smith, B., Garrison, T.M., 2017. Development and validation of a questionnaire to assess pedestrian receptivity toward fully autonomous vehicles. Transport. Res. C Emerg. Technol. 84, 178–195.
Crossref Google Scholar
 

El Hamdani, S., Benamar, N., Younis, M., 2020. Pedestrian support in intelligent transportation systems: challenges, solutions and open issues. Transport. Res. C Emerg. Technol. 121, 102856.
Crossref Google Scholar
 

Ganin, A.A., Mersky, A.C., Jin, A.S., Kitsak, M., Keisler, J.M., Linkov, I., 2019. Resilience in intelligent transportation systems (ITS). Transport. Res. C Emerg. Technol. 100, 318–329.
Crossref Google Scholar
 

Gao, K., Yang, Y., Qu, X., 2021. Diverging effects of subjective prospect values of uncertain time and money. Commun. Transport. Res. 1, 100007.
Crossref Google Scholar
 
Garnelo, M., Schwarz, J., Rosenbaum, D., Viola, F., Rezende, D.J., Eslami, S.M., Teh, Y.W., 2018. Neural processes. In: Proceedings of the International Conference on Machine Learning (ICML).
 

Hochreiter, S., Schmidhuber, J., 1997. Long short-term memory. Neural Comput. 9 (8), 1735–1780.
Crossref Google Scholar
 

Huang, F., Yi, P., Wang, J., Li, M., Peng, J., Xiong, X., 2022. A dynamical spatial-temporal graph neural network for traffic demand prediction. Inf. Sci. 594, 286–304.
Crossref Google Scholar
 

Jia, Y., Wu, J., Xu, M., 2017. Traffic flow prediction with rainfall impact using a deep learning method. J. Adv. Transport., 6575947.
Crossref Google Scholar
 

Kaur, M., Singh, S., Aggarwal, N., 2022. Missing traffic data imputation using a dual-stage error-corrected boosting regressor with uncertainty estimation. Inf. Sci. 586, 344–373.
Crossref Google Scholar
 

Ke, J., Zheng, H., Yang, H., Chen, X.M., 2017. Short-term forecasting of passenger demand under on-demand ride services: a spatio-temporal deep learning approach. Transport. Res. C Emerg. Technol. 85, 591–608.
Crossref Google Scholar
 
Kim, H., Mnih, A., Schwarz, J., Garnelo, M., Eslami, A., Rosenbaum, D., et al., 2019. Attentive neural processes. In: Proceedings of the International Conference on Learning Representations (ICLR).
 
Kingma, D.P., Welling, M., 2014. Auto-encoding variational bayes. In: Proceedings of the International Conference on Learning Representations (ICLR).
 
Kipf, T.N., Welling, M., 2017. Semi-supervised classification with graph convolutional networks. In: Proceedings of the International Conference on Learning Representations (ICLR).
 

Lee, K., Rhee, W., 2022. DDP-GCN: multi-graph convolutional network for spatiotemporal traffic forecasting. Transport. Res. C Emerg. Technol. 134, 103466.
Crossref Google Scholar
 

Li, L., Li, Y., Li, Z., 2013. Efficient missing data imputing for traffic flow by considering temporal and spatial dependence. Transport. Res. C Emerg. Technol. 34, 108–120.
Crossref Google Scholar
 

Li, L., Zhang, J., Wang, Y., Ran, B., 2018. Missing value imputation for traffic-related time series data based on a multi-view learning method. IEEE Trans. Intell. Transport. Syst. 20 (8), 2933–2943.
Crossref Google Scholar
 

Li, H., Li, M., Lin, X., He, F., Wang, Y., 2020. A spatiotemporal approach for traffic data imputation with complicated missing patterns. Transport. Res. C Emerg. Technol. 119, 102730.
Crossref Google Scholar
 

Liu, L., Chen, R.C., 2017. A novel passenger flow prediction model using deep learning methods. Transport. Res. C Emerg. Technol. 84, 74–91.
Crossref Google Scholar
 
Liu, S., Yue, Y., Krishnan, R., 2013. Adaptive collective routing using Gaussian process dynamic congestion models. In: Proceedings of the 19th ACM SIGKDD International Conference On Knowledge Discovery And Data Mining.
Crossref
 

Liu, Q., Wang, B., Zhu, Y., 2018. Short-term traffic speed forecasting based on attention convolutional neural network for arterials. Comput. Aided Civ. Infrastruct. Eng. 33 (11), 999–1016.
Crossref Google Scholar
 

Liu, Y., Liu, Z., Jia, R., 2019. DeepPF: a deep learning based architecture for metro passenger flow prediction. Transport. Res. C Emerg. Technol. 101, 18–34.
Crossref Google Scholar
 

Luan, S., Ke, R., Huang, Z., Ma, X., 2022. Traffic congestion propagation inference using dynamic Bayesian graph convolution network. Transport. Res. C Emerg. Technol. 135, 103526.
Crossref Google Scholar
 

Matthews, A.G.D.G., Van Der Wilk, M., Nickson, T., Fujii, K., Boukouvalas, A., León-Villagrá, P., et al., 2017. GPflow: a Gaussian process library using TensorFlow. J. Mach. Learn. Res. 18 (40), 1–6.
Google Scholar
 

Ni, D., Leonard, J.D., Guin, A., Feng, C., 2005. Multiple imputation scheme for overcoming the missing values and variability issues in ITS data. J. Transport. Eng. 131 (12), 931–938.
Crossref Google Scholar
 

Ortuzar, J.D.D., 2021. Future transportation: sustainability, complexity and individualization of choices. Commun Transport Res 1, 100010.
Crossref Google Scholar
 

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., et al., 2011. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830.
Google Scholar
 

Peng, H., Du, B., Liu, M., Liu, M., Ji, S., Wang, S., et al., 2021. Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning. Inf. Sci. 578, 401–416.
Crossref Google Scholar
 

Qu, L., Li, L., Zhang, Y., Hu, J., 2009. PPCA-based missing data imputation for traffic flow volume: a systematical approach. IEEE Trans. Intell. Transport. Syst. 10 (3), 512–522.
Crossref Google Scholar
 
Rasmussen, C.E., Williams, C.K.I., 2006. Classification. In: Gaussian Processes for Machine Learning. MIT press, Cambridge, MA, pp. 7–32.
Crossref
 

Ran, B., Jin, P.J., Boyce, D., Qiu, T.Z., Cheng, Y., 2012. Perspectives on future transportation research: impact of intelligent transportation system technologies on next-generation transportation modeling. J. Intell. Transport. S. 16 (4), 226–242.
Crossref Google Scholar
 

Rodrigues, F., Pereira, F.C., 2018. Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic data. Transport. Res. C Emerg. Technol. 95, 636–651.
Crossref Google Scholar
 

Rodrigues, F., Henrickson, K., Pereira, F.C., 2018. Multi-output Gaussian processes for crowdsourced traffic data imputation. IEEE Trans. Intell. Transport. Syst. 20 (2), 594–603.
Crossref Google Scholar
 

Salamanis, A., Kehagias, D.D., Filelis-Papadopoulos, C.K., Tzovaras, D., Gravvanis, G.A., 2016. Managing spatial graph dependencies in large volumes of traffic data for travel-time prediction. IEEE Trans. Intell. Transport. Syst. 17 (6), 1678–1687.
Crossref Google Scholar
 

Smith, B.L., Williams, B.M., Oswald, R.K., 2002. Comparison of parametric and nonparametric models for traffic flow forecasting. Transport. Res. C Emerg. Technol. 10 (4), 303–321.
Crossref Google Scholar
 

Spana, S., Du, L., 2022. Optimal information perturbation for traffic congestion mitigation: Gaussian process regression and optimization. Transport. Res. C Emerg. Technol. 138, 103647.
Crossref Google Scholar
 

Sumalee, A., Ho, H.W., 2018. Smarter and more connected: future intelligent transportation system. IATSS Res. 42 (2), 67–71.
Crossref Google Scholar
 

Ta, X., Liu, Z., Hu, X., Yu, L., Sun, L., Du, B., 2022. Adaptive Spatio-Temporal Graph Neural Network for Traffic Forecasting. Knowledge-Based Systems, 108199.
Crossref Google Scholar
 

Tang, J., Zeng, J., 2022. Spatiotemporal gated graph attention network for urban traffic flow prediction based on license plate recognition data. Comput. Aided Civ. Infrastruct. Eng. 37 (1), 3–23.
Crossref Google Scholar
 

Tang, J., Zhang, X., Yin, W., Zou, Y., Wang, Y., 2021. Missing data imputation for traffic flow based on combination of fuzzy neural network and rough set theory. J. Intell. Transport. S. 25 (5), 439–454.
Crossref Google Scholar
 

Tian, Y., Zhang, K., Li, J., Lin, X., Yang, B., 2018. LSTM-based traffic flow prediction with missing data. Neurocomputing 318, 297–305.
Crossref Google Scholar
 

Wang, W., Wu, Y., 2021. Is uncertainty always bad for the performance of transportation systems? Commun. Transport. Res. 1, 100021.
Crossref Google Scholar
 

Xu, M., Di, Y., Yang, H., Chen, X., Zhu, Z., 2023. Multi-task supply-demand prediction and reliability analysis for docked bike-sharing systems via transformer-encoder-based neural processes. Transport. Res. C Emerg. Technol. 147, 104015.
Crossref Google Scholar
 

Yang, B., Kang, Y., Yuan, Y., Huang, X., Li, H., 2021a. ST-LBAGAN: spatio-temporal learnable bidirectional attention generative adversarial networks for missing traffic data imputation. Knowl. Base Syst. 215, 106705.
Crossref Google Scholar
 

Yang, J.M., Peng, Z.R., Lin, L., 2021b. Real-time spatiotemporal prediction and imputation of traffic status based on LSTM and Graph Laplacian regularized matrix factorization. Transport. Res. C Emerg. Technol. 129, 103228.
Crossref Google Scholar
 

Ye, J., Xue, S., Jiang, A., 2021. Attention-based spatio-temporal graph convolutional network considering external factors for multi-step traffic flow prediction. Digital Communications and Networks 8 (3), 343–350.
Crossref Google Scholar
 
Yu, B., Yin, H., Zhu, Z., 2017. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).
Crossref
 

Yuan, Y., Zhang, Z., Yang, X.T., Zhe, S., 2021. Macroscopic traffic flow modeling with physics regularized Gaussian process: a new insight into machine learning applications in transportation. Transp. Res. Part B Methodol. 146, 88–110.
Crossref Google Scholar
 
Zhang, J., Zheng, Y., Qi, D., 2017. Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence.
Crossref
 

Zhang, Y., Cheng, T., Ren, Y., 2019. A graph deep learning method for short-term traffic forecasting on large road networks. Comput. Aided Civ. Infrastruct. Eng. 34 (10), 877–896.
Crossref Google Scholar
 

Zhang, K., He, Z., Zheng, L., Zhao, L., Wu, L., 2021a. A generative adversarial network for travel times imputation using trajectory data. Comput. Aided Civ. Infrastruct. Eng. 36 (2), 197–212.
Crossref Google Scholar
 

Zhang, Z., Lin, X., Li, M., Wang, Y., 2021b. A customized deep learning approach to integrate network-scale online traffic data imputation and prediction. Transport. Res. C Emerg. Technol. 132, 103372.
Crossref Google Scholar
 

Zhu, Z., Peng, B., Xiong, C., Zhang, L., 2016. Short-term traffic flow prediction with linear conditional Gaussian Bayesian network. J. Adv. Transport. 50 (6), 1111–1123.
Crossref Google Scholar
 

Zhu, Z., Mardan, A., Zhu, S., Yang, H., 2021. Capturing the interaction between travel time reliability and route choice behavior based on the generalized Bayesian traffic model. Transp. Res. Part B Methodol. 143, 48–64.
Crossref Google Scholar
 

Zhu, K., Zhang, S., Li, J., Zhou, D., Dai, H., Hu, Z., 2022a. Spatiotemporal multi-graph convolutional networks with synthetic data for traffic volume forecasting. Expert Syst. Appl. 187, 115992.
Crossref Google Scholar
 

Zhu, Z., Xu, M., Di, Y., Chen, X., Yu, J., 2022b. Modeling ride-sourcing matching and pickup processes based on additive Gaussian process models. Transport. Bus.: Transport Dynamics 11 (1), 590–611.
Crossref Google Scholar
 

Zhu, Z., Xu, M., Di, Y., Yang, H., 2022c. Fitting spatial-temporal data via a physics regularized multi-output grid Gaussian process: case studies of a bike-sharing system. IEEE Trans. Intell. Transport. Syst. 23 (11), 21090–21101.
Crossref Google Scholar
 

Zhu, Z., Xu, M., Ke, J., Yang, H., Chen, X., 2023. A Bayesian clustering ensemble Gaussian process model for network-wide traffic flow clustering and prediction. Transport. Res. C Emerg. Technol. 148, 104032.
Crossref Google Scholar
Communications in Transportation Research
Volume 3,
December 2023
Article number: 100099
DOI: 10.1016/j.commtr.2023.100099
Cite this article:
Xu M, Di Y, Ding H, et al. AGNP: Network-wide short-term probabilistic traffic speed prediction and imputation. Communications in Transportation Research, 2023, 3: 100099. https://doi.org/10.1016/j.commtr.2023.100099

295

Views

15

Crossref

15

Web of Science

14

Scopus

Altmetrics
Received: 22 March 2023
Revised: 04 June 2023
Accepted: 04 June 2023
Published: 25 July 2023
© 2023 The Authors.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return