Abstract
Real-time traffic planning and scheduling optimization are critical for developing low-cost, reliable, resilient, and efficient transport systems. In this paper, we present a real-time application that uses machine learning techniques to forecast the train carriage load when a train departure from a platform. With the predicted carriage load, crew can efficiently manage passenger flow, improving the efficiency of boarding and alighting, and thereby reducing the time trains spend at stations. We developed the application in collaboration with Sydney Trains. Most data are publicly available on Open Data Hub, which is supported by the Transport for NSW. We investigated the performance of different models, features, and measured their contributions to prediction accuracy. From this we propose a novel learning strategy, called Multi-Stream Learning, which merges streams having similar concept drift patterns to boost the training data size with the aim of achieving lower generalization errors. We have summarized our solutions and hope researchers and industrial users who might be facing similar problems will benefit from our findings.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li, Z., Hensher, D.A.: Crowding in public transport: a review of objective and subjective measures. J. Public Transp. 16, 107–134 (2013). https://doi.org/10.5038/2375-0901.16.2.6
Campigotto, P., Rudloff, C., Leodolter, M., Bauer, D.: Personalized and situation-aware multimodal route recommendations: the FAVOUR algorithm. IEEE Trans. Intell. Transp. Syst. 1(18), 92–102 (2017). https://doi.org/10.1109/TITS.2016.2565643
Vandewiele, G., Van Herwegen F.O.J., Colpaert, P., De Turck, R.V.F., Janssens, O., Mannens, E.: Predicting train occupancies based on query logs and external data sources. In: 26th International World Wide Web Conference, pp. 1469–1474. ACM, Australia (2019). https://doi.org/10.1145/3041021.3051699
Lu, J., Liu, A., Song, Y., Zhang, G.: Data-driven decision support under concept drift in streamed big data. Complex Intell. Syst. 6(1), 157–163 (2019). https://doi.org/10.1007/s40747-019-00124-4
TfNSW, Tfnsw Open Data Hub And Developer Portal (2020). https://opendata.transport.nsw.gov.au/user-guide
Yu, H., Lu, J., Zhang, G.: Continuous support vector regression for nonstationary streaming data. IEEE Trans. Cybern., 1–14 (2020). https://doi.org/10.1109/TCYB.2020.3015266
Liu, A., Lu, J., Zhang, G.: Concept drift detection via equal intensity k-means space partitioning. IEEE Trans. Cybern., 1–14 (2020). https://doi.org/10.1109/tcyb.2020.2983962
TrainWiki, Sydney Trains (2020). https://nswtrains.fandom.com/wiki/Sydney_Trains
TfNSW, Waratah Trains (2020). https://transportnsw.info/travel-info/ways-to-get-around/train/fleet-facilities/waratah-trains
Abadi, A., Rajabioun, T., Ioannou, P.A.: Traffic flow prediction for road transportation networks with limited traffic data. Ieee Trans. Intell. Transp. Syst. 2(16), 653–662 (2015)
Yu, H., Lu, J., Zhang, G.: Online topology learning by a gaussian membership-based self-organizing incremental neural network. IEEE Trans. Neural Networks Learn. Syst., 1–15 (2020). https://doi.org/10.1109/TNNLS.2019.2947658
Toqúe, F., Côme, E., Mahrsi, M.K. El, Oukhellou, L.: Forecasting dynamic public transport origin-destination matrices with long-short term memory recurrent neural networks. In: 19th International Conference on Intelligent Transportation Systems, Proceedings, pp. 1071–1076. IEEE, Brazil (2016). https://doi.org/10.1109/ITSC.2016.7795689
Chow, D., Liu, A., Zhang, G., Lu, J.: Knowledge graph-based entity importance learning for multi-stream regression on Australian fuel price forecasting. In: Proceedings of International Joint Conference Neural Networks, pp. 1–8. IEEE, Hungary (2019). https://doi.org/10.1109/IJCNN.2019.8851790
Chung, W., Kim, J., Lee, H., Kim, E.: General dimensional multiple-output support vector regressions and their multiple kernel learning. IEEE Trans. Cybern. 11(45), 2572–2584 (2015). https://doi.org/10.1109/TCYB.2014.2377016
Kocev, D., Vens, C., Struyf, J., Džeroski, S.: Tree ensembles for predicting structured outputs. Pattern Recogn. 3(46), 817–833 (2013). https://doi.org/10.1016/j.patcog.2012.09.023
Borchani, H., Varando, G., Bielza, C., Larrañaga, P.: A survey on multi-output regression. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 5(5), 216–233 (2015). https://doi.org/10.1002/widm.1157
Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. In: 31st Conference on Neural Information Processing Systems, pp. 3147–3155. ACM, USA (2017)
Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2012). https://doi.org/10.1007/s13398-014-0173-7.2
Lu, N., Lu, J., Zhang, G., Lopez De Mantaras, R.: A concept drift-tolerant case-base editing technique. Artif. Intell. 230, 108–133 (2016). https://doi.org/10.1016/j.artint.2015.09.009
Lu, N., Zhang, G., Lu, J.: Concept drift detection via competence models. Artif. Intell. 209, 11–28 (2014). https://doi.org/10.1016/j.artint.2014.01.001
Wang, B., et al.: Deep uncertainty quantification: a machine learning approach for weather forecasting. In: Proceedings of ACM SIGKDD International Conference Knowledge Discovery Data Mining, pp. 2087–2095 (2019). https://doi.org/10.1145/3292500.3330704
Lu, J., Zuo, H., Zhang, G.: Fuzzy multiple-source transfer learning. IEEE Trans. Fuzzy Syst. 6706, 1–14 (2019). https://doi.org/10.1109/tfuzz.2019.2952792
Acknowledgement
This study was undertaken as part of the carriage load prediction project coordinated by Sydney Trains (PRO20-9756), and supported by the Australian Research Council (ARC) under Discovery Grant DP190101733 and Laureate project FL190100149.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, H., Liu, A., Wang, B., Li, R., Zhang, G., Lu, J. (2020). Real-Time Decision Making for Train Carriage Load Prediction via Multi-stream Learning. In: Gallagher, M., Moustafa, N., Lakshika, E. (eds) AI 2020: Advances in Artificial Intelligence. AI 2020. Lecture Notes in Computer Science(), vol 12576. Springer, Cham. https://doi.org/10.1007/978-3-030-64984-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-64984-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64983-8
Online ISBN: 978-3-030-64984-5
eBook Packages: Computer ScienceComputer Science (R0)