Short-Term Subway Inbound Passenger Flow Prediction Based on AFC Data and PSO-LSTM Optimized Model

Abstract

Making accurate predictions of subway passenger flow is conducive to optimizing operation plans. This study aims to analyze the regularity of subway passenger flow and combine the modeling skills of deep learning with transportation knowledge to predict the short-term subway passenger flow in the scenarios of workdays and holidays. The processed data were collected from two months of Automated Fare Collection (AFC) data from Xizhimen station of Beijing metro. The data were first cleaned by the established cleansing rules to delete malformed and abnormal logic data. The cleaned data were used to analyze the spatial characteristics in passenger flow. Second, a short-term subway passenger flow prediction model was built on the basis of long short-term memory (LSTM). Determining that the error will be relatively high in peak hours, we proposed gradual optimizations from data input by dividing one whole day into different time periods, and then used particle swarm optimization (PSO) to search for the optimal hyperparameters setting. Finally, inbound passenger flow of Beijing Xizhimen subway station in 2018 was selected for numerical experiments. Predictions of the LSTM-based model had higher accuracy than the traditional machine learning support vector regression (SVR) model, with mean absolute percentage error (MAPE) of 21.97% and 4.80% in the scenarios of workdays and holidays, respectively, which are both lower than those of the SVR model. The optimized PSO-LSTM model has been verified for its effectiveness and accurateness by the AFC data.

Keywords

Short-term subway passenger flow prediction / Deep learning / Long short-term memory / Automated Fare Collection (AFC) data / Particle swarm optimization algorithm

References

[1] He J. Urban Railway traffic passenger flow statistical characteristics analysis and empirical study on the combination forecast method, 2013, Beijing: Beijing Jiaotong University

[2] Zhao J, Gao Y, Yang Z, Li J, Feng Y, Qin Z, Bai Z. Truck traffic speed prediction under non-recurrent congestion: Based on optimized deep learning algorithms and GPS Data. IEEE Access, 2019, 7(1): 9116-9127

[3] Wang X. Study on accessibility of urban public transit based on smart card data, 2018, Beijing: Beijing Jiaotong University

[4] Zhao J, Shi J, Sun Q, Ren L, Liu C. Short-time Inflow and outflow prediction of metro stations based on hybrid deep learning. J Transp Syst Eng Inf Technol, 2020, 20(5): 128-134

[5] Hou C, Sun H, Zhou Y, Cao B, Fan J. Prediction service of subway short-term passenger flow based on neural network. Journal of Chinese Computer Systems, 2019, 40(1): 226-231

[6] Hamed MM, Al-masaeid HR, Bani S, Zahi M. Short-term prediction of traffic volume in urban arterials[J]. J Transp Eng, 1995, 121(3): 249-254

[7] Wang Y, Han B, Zhang Q, Li D. Forecasting of entering passenger flow volume in Beijing subway based on SARIMA model. J Transp Syst Eng Inf Technol, 2015, 15(6): 205-211

[8] GirakaI O, Selvaraj VK. Short-term prediction of intersection turning volume using seasonal ARIMA model. Transp Lett, 2020, 12(7): 483-490

[9] Cui H, Chen X, Yang C, Xiang Y, Duan H. Forecast of subway inbound passenger flow based on DLSTM recurrent network. Urban Mass Transit, 2019, 22(09): 41-45

[10] Liu Y, Liu Z, Jia R. DeepPF: A deep learning based architecture for metro passenger flow prediction. Transp Res Part C: Emerg Technol, 2019, 101: 18-34

[11] Ding A, Zhao X, Jiao L (2002). Traffic flow time series prediction based on statistics learning theory. IEEE 5th International Conference on Intelligent Transportation Systems. Inst Electric Electron Eng Inc, pp. 727–730. DOI: https://doi.org/10.1109/ITSC.2002.1041308

[12] Bai Y, Sun Z, Zeng B, Deng J, Li C. A multi-pattern deep fusion model for short-term bus passenger flow forecasting. Appl Soft Comput J, 2017, 58: 669-680

[13] Hao S, Lee D, Zhao D. Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system. Transp Res Part C: Emerg Technol, 2019, 107: 287-300

[14] Tsai T, Lee C, Wei C. Neural network based temporal feature models for short-term railway passenger demand forecasting. Exp Syst Appl, 2009, 36(2): 3728-3736

[15] Yang J, Zhu J, Liu B, Feng C, Zhang H. Short-term passenger flow prediction for urban railway transit based on combined mode. J Transp Syst Eng Inf Technol, 2019, 19(3): 119-125

[16] Liu Y, Zou B, Ni A, Gao L, Zhang C. Calibrating microscopic traffic simulators using machine learning and particle swarm optimization. Transp Lett, 2021, 13(4): 295-307

[17] Zhao J, Wang X. Vehicle-logo recognition based on modified HU invariant moments and SVM. Multimed Tools Appl, 2019, 78(1): 75-97

[18] Lin L, He Z, Peeta S. Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach. Transp Res Part C Emerg Technol, 2018, 97: 258-276

[19] Du B, Peng H, Wang S, Bhuiyan MZA, Wang L, Gong Q, Liu L, Li J. Deep irregular convolutional residual LSTM for urban traffic passenger flows prediction. IEEE Trans Intell Transp Syst, 2020, 21(3): 972-985

[20] Lv Y, Duan Y, Kang W, Li Z, Wang F. Traffic flow prediction with big data: A deep learning approach. IEEE Trans Intell Transp Syst, 2015, 16(2): 865-873

[21] Du Y. The research and implementation of Beijing subway passenger flow prediction system, 2015, Beijing: Beijing Jiaotong University

[22] Sha S, Li J, Zhang K, Yang Z, Wei LX, Zhu X. RNN-Based subway passenger flow rolling prediction. IEEE ACCESS, 2020, 8: 15232-15240

[23] Zhao J, Gao Y, Bai Z, Wang H, Lu S. Traffic speed prediction under non-recurrent congestion: Based on LSTM method and beidou navigation satellite system data. IEEE Intell Transp Syst Mag, 2019, 11(2): 70-81

[24] Li M, Li J, Wei Z, Wang S, Chen L. Short-time passenger flow forecasting at subway station based on deep learning LSTM structure. Urban Mass Trans, 2018, 21(11): 42-49

[25] Li W, Feng F, Jiang Q. Prediction for railway passenger volume based on modified PSO optimized LSTM neural network. J Railway Sci Eng, 2018, 15(12): 3274-3280

[26] Zhao J, Gao Y, Guo Y, Bai Z. Travel time prediction of expressway based on multi-dimensional data and the particle swarm optimization–autoregressive moving average with exogenous input model. Adv Mech Eng, 2018, 10(2): 1-16

[27] Long X, Li J, Chen Y. Metro short-term traffic flow prediction with deep learning. Control and Decision, 2019, 34(08): 1589-1600

[28] Wang X. Research on short-term passenger flow forecast of urban rail transit line, 2017, Beijing: Beijing Jiaotong University

[29] Qin Y. Short-term passenger flow forecast of urban rail transit stations based on AFC data, 2019, Beijing: Beijing Jiaotong University

[30] Zhao Y, Xia L, Jiang X. Short-term metro passenger flow prediction based on EMD-LSTM. J Traffic and Trans Eng, 2020, 20(04): 194-204

[31] Liang D, Xu J, Li S, Sun C (2020) Short-term passenger flow prediction of rail transit based on VMD-LSTM neural network combination model. Proceedings of the 32nd Chinese Control and Decision Conference, CCDC 2020, Institute of Electrical and Electronics Engineers Inc, pp. 5131-5136. DOI: https://doi.org/10.1109/CCDC49329.2020.9164470

Funding

the National Key Research and Development Program of China(2019YFB1600200)

National Natural Science Foundation of China(71871011)