Designing a Novel Two-Stage Fusion Framework to Predict Short-Term Origin–Destination Flow
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 149, Issue 5
Abstract
Short-term origin-destination (OD) demand predicting plays an indispensable role in intelligent transportation systems and ride-hailing service operations. However, most studies are carried out in trip ends travel demand prediction, i.e., trip generation/attraction, while paying less attention to predicting OD flows in citywide traffic management. To this end, a novel generalized framework is proposed, named two-stage fusion framework (). consists of two stages, where the first stage utilizes an attention-based spatio-temporal graph convolutional network (AST-GCN) to predict the trip generation/attraction, and the second stage develops a modified Kalman filter (KF) to predict OD flow which is converted into a coefficient matrix. Lastly, the final predicted OD can be obtained by integrating the trip generation/attraction and the coefficient matrix. In AST-GCN, a gated fusion mechanism and dynamical zone proximity matrix are applied to improve the capacity of capturing the spatio-temporal interdependence among traffic analysis zones. In KF, we redefine the state vector and observed vector and their covariance matrixes, and then introduce the Box-Cox technique to standardize the deviation matrix to adapt to KF. The proposed model is tested on a large-scale real-world data set from Chongqing, China, and the results indicate that can achieve a satisfactory performance of short-term OD prediction. Moreover, the proposed framework has the convenient scalability, because either of the two stages is replaceable by other predictors.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This work was supported by National Natural Science Foundation of China (Nos. 51878166 and 71701047) and China Scholarship Council (CSC: 202106090220).
References
Afandizadeh Zargari, S., A. Memarnejad, and H. Mirzahossein. 2021. “Hourly origin–destination matrix estimation using intelligent transportation systems data and deep learning.” Sensors 21 (21): 7080. https://doi.org/10.3390/s21217080.
Bai, J., J. Zhu, Y. Song, L. Zhao, Z. Hou, R. Du, and H. Li. 2021. “A3t-gcn: Attention temporal graph convolutional network for traffic forecasting.” ISPRS Int. J. Geo-Inf. 10 (7): 485. https://doi.org/10.3390/ijgi10070485.
Barceló, J., L. Montero, M. Bullejos, O. Serch, and C. Carmona. 2013. “A kalman filter approach for exploiting bluetooth traffic data when estimating time-dependent OD matrices.” J. Intell. Transp. Syst. 17 (2): 123–141. https://doi.org/10.1080/15472450.2013.764793.
Cao, Y., K. Tang, J. Sun, and Y. Ji. 2021. “Day-to-day dynamic origin–destination flow estimation using connected vehicle trajectories and automatic vehicle identification data.” Transp. Res. Part C Emerging Technol. 129 (Aug): 103241. https://doi.org/10.1016/j.trc.2021.103241.
Chen, Y., Z. Wang, H. Sun, Y. Zhang, and Z. He. 2022. “Analysis of travel demand between transportation hubs in urban agglomeration based on mobile phone call detail record data.” J. Transp. Eng. Part A Syst. 148 (7): 04022041. https://doi.org/10.1061/JTEPBS.0000693.
Cheng, Z., M. Trépanier, and L. Sun. 2022. “Real-time forecasting of metro origin-destination matrices with high-order weighted dynamic mode decomposition.” Transp. Sci. 56 (4): 904–918. https://doi.org/10.1287/trsc.2022.1128.
Djukic, T., G. Flötteröd, H. Van Lint, and S. Hoogendoorn. 2012. “Efficient real time OD matrix estimation based on principal component analysis.” In Proc., 2012 15th Int. IEEE Conf. Intelligence Transportation Systems, 115–121. New York: IEEE. https://doi.org/10.1109/ITSC.2012.6338720.
Du, B., X. Hu, L. Sun, J. Liu, Y. Qiao, and W. Lv. 2020. “Traffic demand prediction based on dynamic transition convolutional neural network.” IEEE Trans. Intell. Transp. Syst. 22 (2): 1237–1247. https://doi.org/10.1109/TITS.2020.2966498.
Fu, C., and T. Sayed. 2021. “Random parameters Bayesian hierarchical modeling of traffic conflict extremes for crash estimation.” Accid. Anal. Prev. 157 (Jul): 106159. https://doi.org/10.1016/j.aap.2021.106159.
Fu, C., and T. Sayed. 2022. “Random-parameter Bayesian hierarchical extreme value modeling approach with heterogeneity in means and variances for traffic conflict–based crash estimation.” J. Transp. Eng. Part A Syst. 148 (9): 1–10. https://doi.org/10.1061/JTEPBS.0000717.
Guo, J., Y. Liu, X. Li, W. Huang, J. Cao, and Y. Wei. 2019a. “Enhanced least square based dynamic OD matrix estimation using radio frequency identification data.” Math. Comput. Simul. 155 (Jan): 27–40. https://doi.org/10.1016/j.matcom.2017.10.014.
Guo, S., Y. Lin, N. Feng, C. Song, and H. Wan. 2019b. “Attention based spatio-temporal graph convolutional networks for traffic flow forecasting.” In Proc., AAAI Conf. Artificial Intelligence, 922–929. Palo Alto, CA: Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v33i01.3301922.
He, K., X. Zhang, S. Ren, and J. Sun. 2016. “Deep residual learning for image recognition.” Proc., IEEE Conf. Computer Vision and Pattern Recognition, 770–778. New York: IEEE. https://doi.org/10.1109/CVPR.2016.90.
Huang, J., B. Huang, W. Yu, J. Xiao, R. Xie, and K. Ruan. 2022. “ODformer: Spatio-temporal transformers for long sequence origin-destination matrix forecasting against cross application scenario.” Preprint, submitted August 18, 2022. http://arxiv.org/abs/2208.08218.
Jiang, X., G. Zhang, Y. Zhou, L. Xia, and Z. He. 2017. “Safety assessment of signalized intersections with through-movement waiting area in China.” Saf. Sci. 95 (Aug): 28–37. https://doi.org/10.1016/j.ssci.2017.01.013.
Ke, J., X. Qin, H. Yang, Z. Zheng, Z. Zhu, and J. Ye. 2021. “Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network.” Transp. Res. Part C Emerging Technol. 122 (Jan): 102858. https://doi.org/10.1016/j.trc.2020.102858.
Li, W., X. Yang, X. Tang, and S. Xia. 2020. “SDCN: Sparsity and diversity driven correlation networks for traffic demand forecasting.” In Proc., Int. Joint Conf. on Neural Networks (IJCNN), 1–7. New York: IEEE. https://doi.org/10.1109/IJCNN48605.2020.9207433.
Ma, W., and Z. S. Qian. 2018. “Estimating multi-year 24/7 origin-destination demand using high-granular multi-source traffic data.” Transp. Res. Part C Emerging Technol. 96 (Nov): 96–121. https://doi.org/10.1016/j.trc.2018.09.002.
Mo, B., R. Li, and J. Dai. 2020. “Estimating dynamic origin–destination demand: A hybrid framework using license plate recognition data.” Comput. Civ. Infrastruct. Eng. 35 (7): 734–752. https://doi.org/10.1111/mice.12526.
MXNet. 2018. A flexible and efficient library for deep learning. Wilmington, DE: The Apache Software Foundation.
Prettenhofer, P., and G. Louppe. 2014. “Gradient boosted regression trees in scikit-learn.” Accessed February 24, 2014. https://dokumen.tips/technology/gradient-boosted-regression-trees-in-scikit-learn.html?page=1.
Pu, Z., Z. Li, Y. Jiang, and Y. Wang. 2020. “Fu bll Bayesianefore-after analysis of safety effects of variable speed limit system.” IEEE Trans. Intell. Transp. Syst. 22 (2): 964–976. https://doi.org/10.1109/TITS.2019.2961699.
Sakia, R. M. 1992. “The Box-Cox transformation technique: A review.” J. R. Stat. Soc. D 41 (2): 169–178. https://doi.org/10.2307/2348250.
Shao, H., W. H. K. Lam, A. Sumalee, A. Chen, and M. L. Hazelton. 2014. “Estimation of mean and covariance of peak hour origin–destination demands from day-to-day traffic counts.” Transp. Res. Part B Methodol. 68 (Oct): 52–75. https://doi.org/10.1016/j.trb.2014.06.002.
Shi, X., Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W. Woo. 2015. “Convolutional LSTM network: A machine learning approach for precipitation nowcasting.” Adv. Neural Inf. Process. Syst. 28 (1): 802–810. https://doi.org/10.48550/arXiv.1506.04214.
Shuai, C., W. Wang, G. Xu, M. He, and J. Lee. 2022. “Short-term traffic flow prediction of expressway considering spatial influences.” J. Transp. Eng. Part A Syst. 148 (6): 04022026. https://doi.org/10.1061/JTEPBS.0000660.
Van Zuylen, H. J., and L. G. Willumsen. 1980. “The most likely trip matrix estimated from traffic counts.” Transp. Res. Part B Methodol. 14 (3): 281–293. https://doi.org/10.1016/0191-2615(80)90008-9.
Wang, B., X. Luo, F. Zhang, B. Yuan, A. L. Bertozzi, and P. J. Brantingham. 2018. “Graph-based deep modeling and real time forecasting of sparse spatio-temporal data.” Preprint, submitted December 18, 2022. http://arxiv.org/abs/1804.00684.
Wang, B., P. Yin, A. L. Bertozzi, P. J. Brantingham, S. J. Osher, and J. Xin. 2019. “Deep learning for real-time crime forecasting and its ternarization.” Chin. Ann. Math. Ser. B 40 (6): 949–966. https://doi.org/10.1007/s11401-019-0168-y.
Wu, C.-H., J.-M. Ho, and D.-T. Lee. 2004. “Travel-time prediction with support vector regression.” IEEE Trans. Intell. Transp. Syst. 5 (4): 276–281. https://doi.org/10.1109/TITS.2004.837813.
Wu, Z., S. Pan, G. Long, J. Jiang, and C. Zhang. 2019. “Graph wavenet for deep spatio-temporal graph modeling.” Preprint, submitted July 5, 2022. http://arxiv.org/abs/1906.00121.
Xie, P., T. Li, J. Liu, S. Du, X. Yang, and J. Zhang. 2020. “Urban flow prediction from spatiotemporal data using machine learning: A survey.” Inf. Fusion 59 (Jul): 1–12. https://doi.org/10.1016/j.inffus.2020.01.002.
Xiong, X., K. Ozbay, L. Jin, and C. Feng. 2020. “Dynamic origin–destination matrix prediction with line graph neural networks and Kalman filter.” Transp. Res. Rec. 2674 (8): 491–503. https://doi.org/10.1177/0361198120919399.
Yao, H., X. Tang, H. Wei, G. Zheng, and Z. Li. 2019. “Revisiting spatio-temporal similarity: A deep learning framework for traffic prediction.” In Proc., AAAI Conf. Artificial Intelligence, 5668–5675. Palo Alto, CA: Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v33i01.33015668.
Yao, H., F. Wu, J. Ke, X. Tang, Y. Jia, S. Lu, P. Gong, J. Ye, and Z. Li. 2018. “Deep multi-view spatio-temporal network for taxi demand prediction.” In Proc., AAAI Conf. Artificial Intelligence. Palo Alto, CA: Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v32i1.11836.
Ye, J., J. Zhao, F. Zheng, and C. Xu. 2021. “Completion and augmentation based spatiotemporal deep learning approach for short-term metro origin-destination matrix prediction under limited observable data.” Neural Comput. Appl. 1–16. https://doi.org/10.1007/s00521-022-07866-2.
Yu, B., H. Yin, and Z. Zhu. 2018. “Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting.” Preprint, submitted September 14, 2017. http://arxiv.org/abs/1709.04875.
Zhang, J., H. Che, F. Chen, W. Ma, and Z. He. 2021. “Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method.” Transp. Res. Part C Emerging Technol. 124 (Mar): 102928. https://doi.org/10.1016/j.trc.2020.102928.
Zhang, J., Y. Zheng, and D. Qi. 2017. “Deep spatio-temporal residual networks for citywide crowd flows prediction.” In Proc., 31st AAAI Conf. Artificial Intelligence AAAI 2017. Palo Alto, CA: Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v31i1.10735.
Zheng, C., X. Fan, C. Wang, and J. G. Qi. 2019. “A graph multi-attention network for traffic prediction.” In Proc., 34th AAAI Conf. Artificial Intelligence. Palo Alto, CA: Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v34i01.5477.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 149 • Issue 5 • May 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Jun 14, 2022
Accepted: Jan 18, 2023
Published online: Mar 13, 2023
Published in print: May 1, 2023
Discussion open until: Aug 13, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Dan Peng, Mingxia Huang, Zhibo Xing, Taxi origin and destination demand prediction based on deep learning: a review, Digital Transportation and Safety, 10.48130/DTS-2023-0014, 2, 3, (176-189), (2023).