Abstract
Accurate and high-resolution passenger volume forecasting is very important for the scheduling and regulation of urban railway trains, both to satisfy the quality of railway service and reduce operation cost. This work proposes a Long Short-Term Memory (LSTM) based method to forecast passenger flow in a railway line. By using LSTM time series forecast model, it not only can adapt to the non-linearity and randomness of subway passenger flow, but also prevent the consequences of gradient explosion. A LSTM network is formulated in this work to forecast the passenger volume for workdays and rest days separately. Actual data from Beijing Metro Line 13 is used to train and test the proposed LSTM network, where 90% of the data are used for training and the others are used for testing. Experimental results prove the efficiency of the proposed method. In this experiment, the forecasted time window is as small as 15 min, the maximum error of forecast is 25.2%, the average error is 10.45%, and the final root mean square error is less than 30. The proposed method and forecast results are very helpful for timetabling and rescheduling of urban railway systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhao, L., Yao, E., Liu, S., et al.: Passenger flow analysis for the surrounding subway stations of large special event site during dissipation. In: The International Conference on Information Systems for Crisis Response and Management (2017)
Cervero, R., Pattnaik, J.M.: Rail+Property Development: A Mode of Sustainable Transit Finance and Urbanism (2008)
McCulloch, W., Pitts, W.: A logical calculus of ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)
Cong, Z.: Research on demand forecast of passenger transfer of rail transit and intercity railway-taking Beijing as an example. In: Proceedings of 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017). Computer Science and Electronic Technology International Society, Chongqing (2017)
Jin, F., Li, Y.W., Sun, S.L.: Forecasting air passenger demand with a new hybrid ensemble approach. J. Air Transp. Manage. (2020)
McDonald, J.F.: The first Chicago area transportation study projections and plans for metropolitan Chicago in retrospect. Plann. Perspect. 3(3), 245–268 (1988)
Xue, Y.F., Ma, S.: Rounting plan of subway line as it’s extended based on results of passenger flow forecast. J. Transp. Eng. Inf. (2018)
Lu, T.W., Yao, E.J., Liu, S.S., Zhou, W.H.: Short-time forecast of entrance and exit passenger flow for new line of urban rail transit during growth period. J. China Rail. Soc. (2020)
Guo, X.W., Zhou, M.C., Liu, S.X., Qi, L.: Lexicographic multi-objective scatter search for the optimization of sequence-dependent selective disassembly subject to multi-resource constraints. IEEE Trans. Cybern. (2019). https://doi.org/10.1109/tcyb.2019.2901834
Guo, X.W., Zhou, M.C., Liu, S.X., Qi, L.: Multi-resource constrained selective disassembly with maximal profit and minimal energy consumption. IEEE Trans. Autom. Sci. Eng. (2020, in press)
Rumellhart, D.E., Hinton, G.E., Williams, R.J.: Learing representations by back-propagation errors. Nature 323, 533–536 (1986)
Tsai, T.-H.: Neural network based temporal feature models for short-term railway passenger demand forecasting. Expert Syst. Appl. 36, 3728–3736 (2009)
Hou, C.Y., Sun, H., Zhou, Y.F., Cao, B., Fan, J.: Prediction service of subway short-term passenger flow based on neural network. J. Chin. Comput. Syst. (2019)
Describe Recent Advances in Applied Sciences (Impacts of Weather on Short-Term Metro Passenger Flow Forecasting Using a Deep LSTM Neural Network). Science Letter (2020)
Lint, J.W.C.V.: Online learning solutions for freeway travel time prediction. IEEE Trans. Intell. Transp. Syst. (2008, in press)
He, K., Zhang, X., Ren, S., et al.: Going deeper with convolutions. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Washington, DC (2017)
Wu, Y., Tan, H.: Short-term Traffic Flow Forecasting with Spatial-temporal Correlation in a Hybrid Deep Learning Framework, vol. 47, pp. 112–157 (2016)
Liu, Y.L., Lv, X.Y., Wang, Y., Kong, D.Y.: Research on the Application of Radial Basis Function Neural Network Model in Beijing-TianJin Inter-city Passenger Flow Forecast. China Academic Journal Electronic Publishing House (2019)
Fu, R., Zhang, Z., Li, L.: Using LSTM and GRU neural network for traffic speed prediction using remote microwave sensor data. Transp. Res. Part C 54, 187–197 (2015)
Kuremoto, T., Kimura, S., Kobayashi, K., et al.: Time series forecasting using a deep belief network with restricted Boltzmann machines. IEEE Trans. Intell. Transp. Syst. 137, 47–56 (2014)
Tang, Q.S., Cheng, P., Li, N.: Short time forecasting of passenger flow in urban railway using GSO-BPNN method. Technol. Econ. Areas Commun (2018)
Liu, Z.Q., Sun, Y.S.: Driver’s lane change intention recognition based on LSTM and D-S theory. Hebei J. Ind. Sci. Technol. (2020)
Fu, R., Zhang, Z., Li, L.: Using LSTM and GUR Neural Network Methods for Traffic Flow Prediction. Chinese Association of Automation. IEEE (2017)
Zhong, G., Wan, X., Zhang, J., et al.: Characterizing passenger flow for a transportation hub based on mobile phone data. IEEE Trans. Intell. Transp. Syst. 79, 105–137 (2018)
Liu, L., Chen, R.C.: A Novel Passenger Flow Prediction Model Using Deep Learning Approach for Traffic Flow Prediction Research Part C: Emerging Technologies (2018)
Huang, J., Levinson, D.M., Wang, Y., et al.: Tracking job and housing dynamics with smartcard data. Proc. Natl. Acad. U.S.A. 24, 90–108 (2018)
Wen, H.Y., Chen, C.W.: Short-term passenger traffic forecast based on deep learning. J. Guangxi Univ. (2020)
Roos, J., Gavin, G., Bonnevay, S.: A dynamic Bayesian network approach to forecast short-term urban rail passenger flows with incomplete data. Transp. Res. Procedia 43, 112–135 (2017)
Acknowledgement
The work was partially supported by the Fundamental Research Funds for the Central Universities under grant 2019JBM006, the National Key R&D Program of China (2018YFB1201500), the Beijing Natural Science Foundation (L181005) and the Beijing Laboratory of Urban Rail Transit.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kang, L., Liu, H., Chai, M., Lv, J. (2020). A LSTM-Based Passenger Volume Forecasting Method for Urban Railway Systems. In: Qian, J., Liu, H., Cao, J., Zhou, D. (eds) Robotics and Rehabilitation Intelligence. ICRRI 2020. Communications in Computer and Information Science, vol 1335. Springer, Singapore. https://doi.org/10.1007/978-981-33-4929-2_25
Download citation
DOI: https://doi.org/10.1007/978-981-33-4929-2_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4928-5
Online ISBN: 978-981-33-4929-2
eBook Packages: Computer ScienceComputer Science (R0)