IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v15y2023i14p11092-d1195138.html
   My bibliography  Save this article

Traffic Flow Prediction Based on Hybrid Deep Learning Models Considering Missing Data and Multiple Factors

Author

Listed:
  • Wenbao Zeng

    (Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China
    Jiangsu Province Collaborative Innovation Center for Modern Urban Traffic Technologies, Nanjing 210096, China
    National Traffic Management Engineering and Technology Research Centre, Ningbo University Sub-Centre, Ningbo 315211, China)

  • Ketong Wang

    (Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China
    Jiangsu Province Collaborative Innovation Center for Modern Urban Traffic Technologies, Nanjing 210096, China
    National Traffic Management Engineering and Technology Research Centre, Ningbo University Sub-Centre, Ningbo 315211, China)

  • Jianghua Zhou

    (Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China
    Jiangsu Province Collaborative Innovation Center for Modern Urban Traffic Technologies, Nanjing 210096, China
    National Traffic Management Engineering and Technology Research Centre, Ningbo University Sub-Centre, Ningbo 315211, China)

  • Rongjun Cheng

    (Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China
    Jiangsu Province Collaborative Innovation Center for Modern Urban Traffic Technologies, Nanjing 210096, China
    National Traffic Management Engineering and Technology Research Centre, Ningbo University Sub-Centre, Ningbo 315211, China)

Abstract

In the case of missing data, traffic forecasting becomes challenging. Many existing studies on traffic flow forecasting with missing data often overlook the relationship between data imputation and external factors. To address this gap, this study proposes two hybrid models that incorporate multiple factors for predicting traffic flow in scenarios involving data loss. Temperature, rainfall intensity and whether it is a weekday will be introduced as multiple factors for data imputation and forecasting. Predictive mean matching (PMM) and K-nearest neighbor (KNN) can find the data that are most similar to the missing values as the interpolation value. In the forecasting module, bidirectional long short-term memory (BiLSTM) network can extract bidirectional time series features, which can improve forecasting accuracy. Therefore, PMM and KNN were combined with BiLSTM as P-BiLSTM and K-BiLSTM to forecast traffic flow, respectively. Experiments were conducted using a traffic flow dataset from the expressway S6 in Poland, considering various missing scenarios and missing rates. The experimental results showed that the proposed models outperform other traditional models in terms of prediction accuracy. Furthermore, the consideration of whether it is a working day further improves the predictive performance of the models.

Suggested Citation

  • Wenbao Zeng & Ketong Wang & Jianghua Zhou & Rongjun Cheng, 2023. "Traffic Flow Prediction Based on Hybrid Deep Learning Models Considering Missing Data and Multiple Factors," Sustainability, MDPI, vol. 15(14), pages 1-19, July.
  • Handle: RePEc:gam:jsusta:v:15:y:2023:i:14:p:11092-:d:1195138
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/15/14/11092/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/15/14/11092/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Gerko Vink & Laurence E. Frank & Jeroen Pannekoek & Stef Buuren, 2014. "Predictive mean matching imputation of semicontinuous variables," Statistica Neerlandica, Netherlands Society for Statistics and Operations Research, vol. 68(1), pages 61-90, February.
    2. Dong, Hanxuan & Ding, Fan & Tan, Huachun & Zhang, Hailong, 2022. "Laplacian integration of graph convolutional network with tensor completion for traffic prediction with missing data in inter-city highway network," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 586(C).
    3. Little, Roderick J A, 1988. "Missing-Data Adjustments in Large Surveys," Journal of Business & Economic Statistics, American Statistical Association, vol. 6(3), pages 287-296, July.
    4. Cheng, Rongjun & Lyu, Hao & Zheng, Yaxing & Ge, Hongxia, 2022. "Modeling and stability analysis of cyberattack effects on heterogeneous intelligent traffic flow," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 604(C).
    5. Asif Raza & Ming Zhong, 2018. "Hybrid artificial neural network and locally weighted regression models for lane-based short-term urban traffic flow forecasting," Transportation Planning and Technology, Taylor & Francis Journals, vol. 41(8), pages 901-917, November.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Jianqi Li & Wenbao Zeng & Weiqi Liu & Rongjun Cheng, 2024. "Prediction on Demand for Regional Online Car-Hailing Travel Based on Self-Attention Memory and ConvLSTM," Sustainability, MDPI, vol. 16(13), pages 1-18, July.

    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. Adel Bosch & Steven F. Koch, 2021. "Individual and Household Debt: Does Imputation Choice Matter?," Working Papers 202141, University of Pretoria, Department of Economics.
    2. Fernandes, Mario & Hilber, Simon & Sturm, Jan-Egbert & Walter, Andreas, 2023. "Closing the gender gap in academia? Evidence from an affirmative action program," Research Policy, Elsevier, vol. 52(9).
    3. Shu Yang & Jae Kwang Kim, 2020. "Asymptotic theory and inference of predictive mean matching imputation using a superpopulation model framework," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 47(3), pages 839-861, September.
    4. Raymundo M. Campos-Vázquez, 2013. "Efectos de los ingresos no reportados en el nivel y tendencia de la pobreza laboral en México," Ensayos Revista de Economia, Universidad Autonoma de Nuevo Leon, Facultad de Economia, vol. 0(2), pages 23-54, November.
    5. Joost Ginkel & Pieter Kroonenberg, 2014. "Using Generalized Procrustes Analysis for Multiple Imputation in Principal Component Analysis," Journal of Classification, Springer;The Classification Society, vol. 31(2), pages 242-269, July.
    6. Verbeek, M.J.C.M. & Nijman, T.E., 1992. "Incomplete panels and selection bias : A survey," Discussion Paper 1992-7, Tilburg University, Center for Economic Research.
    7. Hendrik Jürges & Lars Thiel & Tabea Bucher-Koenen & Johannes Rausch & Morten Schuth & Axel Börsch-Supan, 2014. "Health, Financial Incentives, and Early Retirement: Microsimulation Evidence for Germany," NBER Chapters, in: Social Security Programs and Retirement Around the World: Disability Insurance Programs and Retirement, pages 285-330, National Bureau of Economic Research, Inc.
    8. Gerko Vink & Laurence E. Frank & Jeroen Pannekoek & Stef Buuren, 2014. "Predictive mean matching imputation of semicontinuous variables," Statistica Neerlandica, Netherlands Society for Statistics and Operations Research, vol. 68(1), pages 61-90, February.
    9. Christopher R. Bollinger & Barry T. Hirsch, 2010. "GDP & Beyond – die europäische Perspektive," RatSWD Working Papers 165, German Data Forum (RatSWD).
    10. Martin, Eisele & Zhu, Junyi, 2013. "Multiple imputation in a complex household survey - the German Panel on Household Finances (PHF): challenges and solutions," MPRA Paper 57666, University Library of Munich, Germany.
    11. Xiong, Ruoxuan & Pelger, Markus, 2023. "Large dimensional latent factor modeling with missing observations and applications to causal inference," Journal of Econometrics, Elsevier, vol. 233(1), pages 271-301.
    12. Dang, Hai-Anh H & Carletto, Calogero, 2022. "Recall Bias Revisited: Measure Farm Labor Using Mixed-Mode Surveys and Multiple Imputation," IZA Discussion Papers 14997, Institute of Labor Economics (IZA).
    13. Hou, Lin & Pei, Yulong & He, Qingling, 2023. "A car following model in the context of heterogeneous traffic flow involving multilane following behavior," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 632(P1).
    14. Daniel Schunk, 2007. "A Markov Chain Monte Carlo Multiple Imputation Procedure for Dealing with Item Nonresponse in the German SAVE Survey," MEA discussion paper series 07121, Munich Center for the Economics of Aging (MEA) at the Max Planck Institute for Social Law and Social Policy.
    15. Brownstone, David, 1997. "Multiple Imputation Methodology for Missing Data, Non-Random Response, and Panel Attrition," University of California Transportation Center, Working Papers qt2zd6w6hh, University of California Transportation Center.
    16. Zachary H. Seeskin, 2016. "Evaluating the Use of Commercial Data to Improve Survey Estimates of Property Taxes," CARRA Working Papers 2016-06, Center for Economic Studies, U.S. Census Bureau.
    17. Eric French & John Bailey Jones, 2011. "The Effects of Health Insurance and Self‐Insurance on Retirement Behavior," Econometrica, Econometric Society, vol. 79(3), pages 693-732, May.
    18. F. Di Lascio & Simone Giannerini & Alessandra Reale, 2015. "Exploring copulas for the imputation of complex dependent data," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 24(1), pages 159-175, March.
    19. Ankita Patnaik & Jeffrey Hemmeter & Arif Mamun, "undated". "Promoting Readiness of Minors with Autism Spectrum Disorder: Evidence from a Randomized Controlled Trial," Mathematica Policy Research Reports a74c93d9bdce40709ad81cdbc, Mathematica Policy Research.
    20. Luci Ellis & Jeremy Lawson & Laura Roberts-Thomson, 2003. "Housing Leverage in Australia," RBA Research Discussion Papers rdp2003-09, Reserve Bank of Australia.

    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:jsusta:v:15:y:2023:i:14:p:11092-:d:1195138. 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.