Abstract
The accurate prediction of short-term passenger flow is of high importance to efficiently manage the passenger flow of metro systems and adjust timetable accordingly. However, the existing methods of passenger flow prediction cannot achieve adequate accurate results due to its complex nonlinear spatiotemporal characteristics. To improve the accuracy of short-term passenger flow prediction, this paper proposes a deep learning model based on a spatiotemporal framework. Firstly, the graph convolutional network, which incorporates prior domain knowledge (such as travel time and origin–destination demand), is used to extract spatial features of passenger flow. Secondly, the attention mechanism is integrated into the gated recurrent unit to extract the time correlation of passenger flow. Finally, external factors are introduced to capture their impact on passenger flow as well. A case study of the Beijing Subway system is illustrated to verify the performance of the proposed model. The results show that compared with the existing models, the proposed model achieves the highest prediction accuracy and strong robustness. Furthermore, we demonstrate that the adjacency matrix based on travel time outperforms the one based on OD demand, especially during evening peak hours. In addition, it is also verified that the attention mechanism and external factors can improve the prediction performance of the proposed model.
Similar content being viewed by others
Data availability
Enquiries about data availability should be directed to the authors.
References
Ahmed MS, Cook AR (1979) Analysis of freeway traffic time-series data by using box-jenkins techniques. Transp Res Rec 1–9
Akiyama T, Inokuchi H (2014) Long term estimation of traffic demand on urban expressway by neural networks. In: 2014 Jt 7th Int Conf Soft Comput Intell Syst SCIS 2014 15th Int Symp Adv Intell Syst ISIS 2014 185–189. https://doi.org/10.1109/SCIS-ISIS.2014.7044899
Al-Janabi S, Rawat S, Patel A, Al-Shourbaji I (2015) Design and evaluation of a hybrid system for detection and prediction of faults in electrical transformers. Int J Electr Power Energy Syst 67:324–335. https://doi.org/10.1016/j.ijepes.2014.12.005
Al-Janabi S, Mohammad M, Al-Sultan A (2020) A new method for prediction of air pollution based on intelligent computation. Soft Comput 24:661–680. https://doi.org/10.1007/s00500-019-04495-1
Al-Janabi S, Alkaim A, Al-Janabi E et al (2021) Intelligent forecaster of concentrations (PM2.5, PM10, NO2, CO, O3, SO2) caused air pollution (IFCsAP). Neural Comput Appl 33:14199–14229. https://doi.org/10.1007/s00521-021-06067-7
Cheng Z, Trepanier M, Sun L (2021) Real-time forecasting of metro origin-destination matrices with high-order weighted dynamic mode decomposition. Transport Rev 24(5):533–557. https://doi.org/10.1287/trsc.2022.1128
Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. Adv Neural Inf Process Syst 3844–3852
Do LNN, Vu HL, Vo BQ et al (2019) An effective spatial-temporal attention based neural network for traffic flow prediction. Transp Res Part C Emerg Technol 108:12–28. https://doi.org/10.1016/j.trc.2019.09.008
Eldan R, Shamir O (2016) The power of depth for feedforward neural networks. J Mach Learn Res 49:907–940
Fu R, Zhang Z, Li L (2017) Using LSTM and GRU neural network methods for traffic flow prediction. In: Proc - 2016 31st Youth Acad Annu Conf Chinese Assoc Autom YAC 2016, pp 324–328. https://doi.org/10.1109/YAC.2016.7804912
Gu Y, Lu W, Xu X et al (2019) An improved bayesian combination model for short-term traffic prediction with deep learning. IEEE Trans Intell Transp Syst Early Acce: https://doi.org/10.1109/TITS.2014.2345663
Guo X, Zhu Q (2009) A traffic flow forecasting model based on BP neural network. In: PEITS 2009 - 2009 2nd Conf Power Electron Intell Transp Syst, vol. 3, pp 311–314. https://doi.org/10.1109/PEITS.2009.5406865
Hao S, Lee DH, Zhao D (2019) Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system. Transp Res Part C Emerg Technol 107:287–300. https://doi.org/10.1016/j.trc.2019.08.005
Haykin S, Kosko B (2010) GradientBased learning applied to document recognition. Intell Signal Process
Hong WC, Dong Y, Zheng F, Lai CY (2011) Forecasting urban traffic flow by SVR with continuous ACO. Appl Math Model 35:1282–1291. https://doi.org/10.1016/j.apm.2010.09.005
Hu Z, Zuo Y, Xue Z et al (2018) Predicting the metro passengers flow by long-short term memory. Lect Notes Electr Eng 474:591–595. https://doi.org/10.1007/978-981-10-7605-3_97
Huang W, Song G, Hong H, Xie K (2014) Deep architecture for traffic flow prediction: deep belief networks with multitask learning. IEEE Trans Intell Transp Syst 15:2191–2201. https://doi.org/10.1109/TITS.2014.2311123
Jiao P, Li R, Sun T et al (2016) Three revised Kalman filtering models for short-term rail transit passenger flow prediction. Math Probl Eng. https://doi.org/10.1155/2016/9717582
Ke J, Zheng H, Yang H, Chen (Michael) X (2017) Short-term forecasting of passenger demand under on-demand ride services: a spatio-temporal deep learning approach. Transp Res Part C Emerg Technol 85:591–608. https://doi.org/10.1016/j.trc.2017.10.016
Kipf TN, Welling M (2019) Semi-supervised classification with graph convolutional networks. In:5th Int Conf Learn Represent ICLR 2017—Conf Track Proc, pp 1–14
Li S, Dessouky MM, Yang L, Gao Z (2017a) Joint optimal train regulation and passenger flow control strategy for high-frequency metro lines. Transp Res Part B Methodol 99:113–137. https://doi.org/10.1016/j.trb.2017.01.010
Li Y, Wang X, Sun S et al (2017b) Forecasting short-term subway passenger flow under special events scenarios using multiscale radial basis function networks. Transp Res Part C Emerg Technol 77:306–328. https://doi.org/10.1016/j.trc.2017.02.005
Li H, Wang Y, Xu X et al (2019) Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network. Appl Soft Comput J 83:105620. https://doi.org/10.1016/j.asoc.2019.105620
Li J, Guo F, Sivakumar A et al (2021) Transferability improvement in short-term traffic prediction using stacked LSTM network. Transp Res Part C Emerg Technol 124:102977. https://doi.org/10.1016/j.trc.2021.102977
Liu Y, Liu Z, Jia R (2019) DeepPF: a deep learning based architecture for metro passenger flow prediction. Transp Res Part C Emerg Technol 101:18–34. https://doi.org/10.1016/j.trc.2019.01.027
Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. In: Conf Proc - EMNLP 2015 Conf Empir Methods Nat Lang Process, pp 1412–1421. https://doi.org/10.18653/v1/d15-1166
Ma X, Zhang J, Du B et al (2019) Parallel architecture of convolutional bi-directional LSTM neural networks for network-wide metro ridership prediction. IEEE Trans Intell Transp Syst 20:2278–2288. https://doi.org/10.1109/TITS.2018.2867042
Mahdi MA, Al_Janabi S (2020) A novel software to improve healthcare base on predictive analytics and mobile services for cloud data centers. Big Data Netw Technol 81:320–339. https://doi.org/10.1007/978-3-030-23672-4_23
Mahmoud N, Abdel-Aty M, Cai Q, Yuan J (2021) Predicting cycle-level traffic movements at signalized intersections using machine learning models. Transp Res Part C Emerg Technol 124:102930. https://doi.org/10.1016/j.trc.2020.102930
Ni M, He Q, Gao J (2017) Forecasting the subway passenger flow under event occurrences with social media. IEEE Trans Intell Transp Syst 18:1623–1632. https://doi.org/10.1109/TITS.2016.2611644
Petridis V, Kehagias A, Petrou L et al (2001) A Bayesian multiple models combination method for time series prediction. J Intell Robot Syst Theory Appl 31:69–89. https://doi.org/10.1023/A:1012061814242
Roy KC, Hasan S, Culotta A, Eluru N (2021) Predicting traffic demand during hurricane evacuation using real-time data from transportation systems and social media. Transp Res Part C Emerg Technol 131:103339. https://doi.org/10.1016/j.trc.2021.103339
Ryu U, Wang J, Kim T et al (2018) Construction of traffic state vector using mutual information for short-term traffic flow prediction. Transp Res Part C Emerg Technol 96:55–71. https://doi.org/10.1016/j.trc.2018.09.015
Shang P, Li R, Guo J et al (2019) Integrating Lagrangian and Eulerian observations for passenger flow state estimation in an urban rail transit network: a space-time-state hyper network-based assignment approach. Transp Res Part B Methodol 121:135–167. https://doi.org/10.1016/j.trb.2018.12.015
Sun L, Lu Y, Jin JG et al (2015a) An integrated Bayesian approach for passenger flow assignment in metro networks. Transp Res Part C Emerg Technol 52:116–131. https://doi.org/10.1016/j.trc.2015.01.001
Sun Y, Leng B, Guan W (2015b) A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system. Neurocomputing 166:109–121. https://doi.org/10.1016/j.neucom.2015.03.085
Toqúe F, Côme E, El MMK, Oukhellou L (2016) Forecasting dynamic public transport origin-destination matrices with long-short term memory recurrent neural networks. IEEE Conf Intell Transp Syst Proc ITSC. https://doi.org/10.1109/ITSC.2016.7795689
Toque F, Khouadjia M, Come E, et al (2018) Short & long term forecasting of multimodal transport passenger flows with machine learning methods. In: IEEE Conf Intell Transp Syst Proceedings, ITSC 2018-March, pp 560–566. https://doi.org/10.1109/ITSC.2017.8317939
Wei Y, Chen MC (2012) Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transp Res Part C Emerg Technol 21:148–162. https://doi.org/10.1016/j.trc.2011.06.009
Williams BM, Hoel LA (2003) Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J Transp Eng 129:664–672. https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664)
Wu Y, Tan H, Qin L et al (2018) A hybrid deep learning based traffic flow prediction method and its understanding. Transp Res Part C Emerg Technol 90:166–180. https://doi.org/10.1016/j.trc.2018.03.001
Yang H, Yonggang W, Hui P et al (2021) Subway passenger flow prediction based on optimized PSO-BP algorithm with coupled spatial temporal characteristics. J Traffic Transport Eng 21(04):210–222. https://doi.org/10.19818/j.cnki.1671-1637.2021.04.016
Yi H, Heejin J, Bae S (2017) Deep Neural Networks for traffic flow prediction. IEEE Int Conf Big Data Smart Comput BigComp 2017:328–331. https://doi.org/10.1109/BIGCOMP.2017.7881687
Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. IJCAI Int Jt Conf Artif Intell. https://doi.org/10.24963/ijcai.2018/505
Yu B, Lee Y, Sohn K (2020) Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN). Transp Res Part C Emerg Technol 114:189–204. https://doi.org/10.1016/j.trc.2020.02.013
Zeng D, Xu J, Gu J, et al (2008) Short term traffic flow prediction based on online learning SVR. In: Proc - 2008 Work Power Electron Intell Transp Syst PEITS 2008, pp 616–620. https://doi.org/10.1109/PEITS.2008.134
Zhang J, Zheng Y, Qi D (2017) Deep spatio-temporal residual networks for citywide crowd flows prediction. In: 31st AAAI Conf Artif Intell AAAI 2017, pp 1655–1661
Zhang D, Wang XC (2014) Transit ridership estimation with network Kriging: a case study of Second Avenue Subway, NYC. J Transp Geogr 41:107–115. https://doi.org/10.1016/j.jtrangeo.2014.08.021
Zhao L, Song Y, Zhang C et al (2019a) T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst 14:1–11. https://doi.org/10.1109/tits.2019.2935152
Zhao L, Song Y, Zhang C et al (2019b) T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst. https://doi.org/10.1109/tits.2019.2935152
Funding
The authors have not disclosed any funding. This project was supported by the National Natural Science Foundation of China (No.71871012) and the Natural Science Foundation of Beijing (No. 9212014).
Author information
Authors and Affiliations
Contributions
XW: was involved in design of methodology; programming; writing the initial draft. XX: helped in critical review, commentary and revision; oversight and leadership responsibility for the research activity planning and execution. YW: and JL contributed to critical review, commentary, and revision.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, X., Xu, X., Wu, Y. et al. An effective spatiotemporal deep learning framework model for short-term passenger flow prediction. Soft Comput 26, 5523–5538 (2022). https://doi.org/10.1007/s00500-022-07025-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-022-07025-8