IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v12y2024i20p3204-d1497593.html
   My bibliography  Save this article

Short-Term Prediction of Origin–Destination Passenger Flow in Urban Rail Transit Systems with Multi-Source Data: A Deep Learning Method Fusing High-Dimensional Features

Author

Listed:
  • Huanyin Su

    (School of Rail Transportation, Wuyi University, Jiangmen 529020, China)

  • Shanglin Mo

    (School of Rail Transportation, Wuyi University, Jiangmen 529020, China)

  • Huizi Dai

    (Guangzhou Metro Group Co., Ltd., Guangzhou 510000, China)

  • Jincong Shen

    (School of Rail Transportation, Wuyi University, Jiangmen 529020, China)

Abstract

Short-term origin–destination (OD) passenger flow forecasting is crucial for urban rail transit enterprises aiming to optimise transportation products and increase operating income. As there are large-scale OD pairs in an urban rail transit system, OD passenger flow cannot be obtained in real time (temporal hysteresis). Additionally, the distribution characteristics are also complex. Previous studies mainly focus on passenger flow prediction at metro stations, while few methods solve the OD passenger flow prediction problems of an urban rail transit system. In view of this, we propose a novel deep learning method fusing high-dimensional features (HDF-DL) with multi-source data. The HDF-DL method is combined with three modules. The temporal module incorporates the time-varying, trend, and cyclic characteristics of OD passenger flow, while the latest OD passenger flow time sequence (within 1 h) is excluded from the time-varying characteristics. In the spatial module, the K-means and K-shape algorithms are used to classify OD pairs from multiple perspectives and capture the spatial features, reducing the difficulty of OD passenger flow predictions with large-scale and complex characteristics. Weather factors are considered in the external feature module. The HDF-DL method is tested on a large-scale metro system in China, in which eight baseline models are designed. The results show that the HDF-DL method achieves high prediction accuracy across multiple time granularities, with a mean absolute percentage error of about 10%. OD passenger flow in every departure time interval can be predicted with high and stable accuracy, effectively capturing temporal characteristics. The modular design of HDF-DL, which fuses high-dimensional features and employs appropriate neural networks for different data types, significantly reduces prediction errors and outperforms baseline models.

Suggested Citation

  • Huanyin Su & Shanglin Mo & Huizi Dai & Jincong Shen, 2024. "Short-Term Prediction of Origin–Destination Passenger Flow in Urban Rail Transit Systems with Multi-Source Data: A Deep Learning Method Fusing High-Dimensional Features," Mathematics, MDPI, vol. 12(20), pages 1-21, October.
    • Handle: RePEc:gam:jmathe:v:12:y:2024:i:20:p:3204-:d:1497593
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/12/20/3204/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/12/20/3204/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Gould, Phillip G. & Koehler, Anne B. & Ord, J. Keith & Snyder, Ralph D. & Hyndman, Rob J. & Vahid-Araghi, Farshid, 2008. "Forecasting time series with multiple seasonal patterns," European Journal of Operational Research, Elsevier, vol. 191(1), pages 207-222, November.
    2. Okutani, Iwao & Stephanedes, Yorgos J., 1984. "Dynamic prediction of traffic volume through Kalman filtering theory," Transportation Research Part B: Methodological, Elsevier, vol. 18(1), pages 1-11, February.
    3. du Preez, Johann & Witt, Stephen F., 2003. "Univariate versus multivariate time series forecasting: an application to international tourism demand," International Journal of Forecasting, Elsevier, vol. 19(3), pages 435-451.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Huanyin Su & Shanglin Mo & Shuting Peng, 2023. "Short-Term Prediction of Time-Varying Passenger Flow for Intercity High-Speed Railways: A Neural Network Model Based on Multi-Source Data," Mathematics, MDPI, vol. 11(16), pages 1-16, August.
    2. Xing, Tao & Zhou, Xuesong & Taylor, Jeffrey, 2013. "Designing heterogeneous sensor networks for estimating and predicting path travel time dynamics: An information-theoretic modeling approach," Transportation Research Part B: Methodological, Elsevier, vol. 57(C), pages 66-90.
    3. Barrow, Devon & Kourentzes, Nikolaos, 2018. "The impact of special days in call arrivals forecasting: A neural network approach to modelling special days," European Journal of Operational Research, Elsevier, vol. 264(3), pages 967-977.
    4. Ling Tang & Chengyuan Zhang & Tingfei Li & Ling Li, 2021. "A novel BEMD-based method for forecasting tourist volume with search engine data," Tourism Economics, , vol. 27(5), pages 1015-1038, August.
    5. Moreno, Manuel & Novales, Alfonso & Platania, Federico, 2019. "Long-term swings and seasonality in energy markets," European Journal of Operational Research, Elsevier, vol. 279(3), pages 1011-1023.
    6. Muhammad Fahim & Alberto Sillitti, 2019. "Analyzing Load Profiles of Energy Consumption to Infer Household Characteristics Using Smart Meters," Energies, MDPI, vol. 12(5), pages 1-15, February.
    7. Nyoni, Thabani & Mutongi, Chipo, 2019. "Modeling and forecasting carbon dioxide emissions in China using Autoregressive Integrated Moving Average (ARIMA) models," MPRA Paper 93984, University Library of Munich, Germany.
    8. Kong, Xiangyu & Li, Chuang & Wang, Chengshan & Zhang, Yusen & Zhang, Jian, 2020. "Short-term electrical load forecasting based on error correction using dynamic mode decomposition," Applied Energy, Elsevier, vol. 261(C).
    9. Barrow, Devon K., 2016. "Forecasting intraday call arrivals using the seasonal moving average method," Journal of Business Research, Elsevier, vol. 69(12), pages 6088-6096.
    10. Niematallah Elamin & Mototsugu Fukushige, 2016. "Forecasting extreme seasonal tourism demand," Discussion Papers in Economics and Business 16-23, Osaka University, Graduate School of Economics.
    11. Nyoni, Thabani, 2019. "Forecasting the population of Brazil using the Box-Jenkins ARIMA approach," MPRA Paper 92437, University Library of Munich, Germany.
    12. Aviral Kumar Tiwari & Claudiu T Albulescu & Phouphet Kyophilavong, 2014. "A comparison of different forecasting models of the international trade in India," Economics Bulletin, AccessEcon, vol. 34(1), pages 420-429.
    13. M. Bierlaire & F. Crittin, 2004. "An Efficient Algorithm for Real-Time Estimation and Prediction of Dynamic OD Tables," Operations Research, INFORMS, vol. 52(1), pages 116-127, February.
    14. David Watling & Giulio Cantarella, 2015. "Model Representation & Decision-Making in an Ever-Changing World: The Role of Stochastic Process Models of Transportation Systems," Networks and Spatial Economics, Springer, vol. 15(3), pages 843-882, September.
    15. Marcos Álvarez-Díaz & Manuel González-Gómez & María Soledad Otero-Giráldez, 2018. "Forecasting International Tourism Demand Using a Non-Linear Autoregressive Neural Network and Genetic Programming," Forecasting, MDPI, vol. 1(1), pages 1-17, September.
    16. Cai, Lingru & Zhang, Zhanchang & Yang, Junjie & Yu, Yidan & Zhou, Teng & Qin, Jing, 2019. "A noise-immune Kalman filter for short-term traffic flow forecasting," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 536(C).
    17. Huayuan Chen & Zhizhe Lin & Yamin Yao & Hai Xie & Youyi Song & Teng Zhou, 2024. "Hybrid Extreme Learning for Reliable Short-Term Traffic Flow Forecasting," Mathematics, MDPI, vol. 12(20), pages 1-15, October.
    18. Nyoni, Thabani, 2019. "Where is Eritrea going in terms of population growth? Insights from the ARIMA approach," MPRA Paper 92435, University Library of Munich, Germany.
    19. Ramli, Azizul Azhar & Watada, Junzo & Pedrycz, Witold, 2011. "Real-time fuzzy regression analysis: A convex hull approach," European Journal of Operational Research, Elsevier, vol. 210(3), pages 606-617, May.
    20. Jiasong Zhu & Anthony Gar-On Yeh, 2012. "A Self-Learning Short-Term Traffic Forecasting System," Environment and Planning B, , vol. 39(3), pages 471-485, June.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:12:y:2024:i:20:p:3204-:d:1497593. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.