Skip to main content
SpringerLink
Log in

Reconciling spatiotemporal conjunction with digital twin for sequential travel time prediction and intelligent routing

  • Original Research
  • Published:
Annals of Operations Research Aims and scope Submit manuscript

Abstract

A traffic digital twin explicitly communicates the primary domain of the digital twin for traffic management and analysis in understanding and simulating traffic patterns, optimizing traffic flow, and addressing related challenges. It characterizes a virtual, computerized representation of the Intelligent Transportation System (ITS), where a digital twin mimics the real-world ITS by integrating real-time data, analysis and simulation to replicate and simulate the behavior, performance and dynamics of the transport system. This study proposes a novel deep learning algorithm, called the Bidirectional Anisometric Gated Recursive Unit (BDAGRU), which is designed for a digital twin to dynamically process current traffic information to predict near-future travel times and support route selection. After formulating the computational procedure using the stochastic gradient descent algorithm, we successfully perform several near-future sequence predictions (ranging from 15 to 150 min) with extensive multimodal (numerical and textual) data, especially under congested traffic conditions. We then determine the most efficient vehicle route by minimizing travel time under uncertainty, using a digital twin enhanced by the BDAGRU-driven deep learning method. Empirical analysis of extensive traffic data shows that our proposed model achieves two notable results: (1) significant improvement in the accuracy of travel time prediction over different time intervals compared to several traditional deep learning methods, and (2) competent determination of the best route with the shortest travel time, especially in scenarios with future uncertainties.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Algorithm 1
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. https://ResearchAndMarkets.com.

  2. A cyber-physical system is an embedded system consisting of interactive elements with physical inputs and outputs, rather than as stand-alone devices, which are composed of computer processors, computer memory, and input/output peripherals within a larger mechanical or electronic system performing specialized functions.

  3. see https://docs.oracle.com, Developing Applications with Oracle Internet of Things Cloud Service.

  4. XML formatters are either online tools or downloadable applications.

  5. The tail error (TE) corresponds to a quantile within the error distribution, ensuring that, particularly in extreme cases, the maximum error in predicting the next step at a given confidence level does not exceed this threshold.

    $$\begin{aligned} \textrm{TE}_{\alpha }\,= & {} \, \inf \{ \varepsilon \in \Re : \textrm{P}(\textrm{Error}>\varepsilon ) \le 1\,-\,\alpha \}, \end{aligned}$$

    and the expected tail error (ETE) is:

    $$\begin{aligned} \textrm{ETE}_{\alpha }\,= & {} \, \frac{1}{1-\alpha }\int _{\alpha }^1 \textrm{TE}_{\varepsilon }\,(\textrm{Error}) \,\textrm{d}\varepsilon , \end{aligned}$$

    where \(\alpha \in (0,1)\) is confidence level and \(\varepsilon \) is the threshold.

  6. Let \(\mu _y\) and \(\mu _{{\hat{y}}}\) are the mean of observed value y and predictive value \({\hat{y}}\) and \(\sigma ^2_y\) and \(\sigma ^2_{{\hat{y}}}\) are the corresponding variances. \(\rho \) is the correlation coefficient between y and \({\hat{y}}\), the concordance measure is:

    $$\begin{aligned} \gamma = \frac{2 \,\rho \,\sigma _y \,\sigma _{{\hat{y}}}}{\sigma ^2_y +\sigma ^2_{{\hat{y}}} +(\mu _y - \mu _{{\hat{y}}})^2 }. \end{aligned}$$

  7. Here, the optimal value is the one that uses the least number of hidden units within the same error margin. So we set \(M=64\) to facilitate the comparison of all deep learning models.

References

  • Avraham, E., & Raviv, T. (2020). The data-driven time-dependent traveling salesperson problem. Transportation Research Part B: Methodological, 134, 25–40.

    Article  Google Scholar 

  • Bar-Gera, H. (2007). Evaluation of a cellular phone-based system for measurements of traffic speeds and travel times: A case study from israel. Transportation Research Part C: Emerging Technologies, 15, 380–391.

    Article  Google Scholar 

  • Bar-Gera, H., Schechtman, E., & Musicant, O. (2017). Evaluating the effect of enforcement on speed distributions using probe vehicle data. Transportation Research Part F: Traffic Psychology and Behaviour, 46, 271–283.

    Article  Google Scholar 

  • Charles, V., Emrouznejad, A., & Gherman, T. (2023). A critical analysis of the integration of blockchain and artificial intelligence for supply chain. Annals of Operations Research, 327, 7–47.

    Article  Google Scholar 

  • Chen, C. Y. T., Sun, E. W., Chang, M. F., & Lin, Y. B. (2023). Enhancing travel time prediction with deep learning on chronological and retrospective time order information of big traffic data. Annals of Operations Research. https://doi.org/10.1007/s10479-023-05223-7

    Article  Google Scholar 

  • Chen, Y., Sun, E., & Lin, Y. (2019). Coherent quality management for big data systems: A dynamic approach for stochastic time consistency. Annals of Operations Research, 277, 3–32.

    Article  Google Scholar 

  • Chen, Y. T., Sun, E. W., Chang, M. F., & Lin, Y. B. (2021). Pragmatic real-time logistics management with traffic IoT infrastructure: Big data predictive analytics of freight travel time for logistics 4.0. International Journal of Production Economics, 238, 108157.

    Article  Google Scholar 

  • Chiou, J. M., Liou, H. T., & Chen, W. H. (2021). Modeling time-varying variability and reliability of freeway travel time using functional principal component analysis. IEEE Transactions on Intelligent Transportation Systems, 22, 257–266.

    Article  Google Scholar 

  • Corredera, A., & Ruiz, C. (2023). Prescriptive selection of machine learning hyperparameters with applications in power markets: Retailer’s optimal trading. European Journal of Operational Research, 306, 370–388.

    Article  Google Scholar 

  • Cui, Z., Ke, R., Pu, Z., & Wang, Y. (2020). Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values. Transportation Research Part C: Emerging Technologies, 118, 102674.

    Article  Google Scholar 

  • Dhaenens, C., & Jourdan, L. (2022). Metaheuristics for data mining: Survey and opportunities for big data. Annals of Operations Research, 314(1), 117.

    Article  Google Scholar 

  • Ding, K., Chan, F. T., Zhang, X., Zhou, G., & Zhang, F. (2019). Defining a digital twin-based cyber-physical production system for autonomous manufacturing in smart shop floors. International Journal of Production Research, 57, 6315–6334.

    Article  Google Scholar 

  • Do, L. N., Vu, H. L., Vo, B. Q., Liu, Z., & Phung, D. (2019). An effective spatial-temporal attention based neural network for traffic flow prediction. Transportation Research Part C: Emerging Technologies, 108, 12–28.

    Article  Google Scholar 

  • Flori, A., & Regoli, D. (2021). Revealing pairs-trading opportunities with long short-term memory networks. European Journal of Operational Research, 295, 772–791.

    Article  Google Scholar 

  • Gao, H., & Liu, F. (2013). Estimating freeway traffic measures from mobile phone location data. European Journal of Operational Research, 229, 252–260.

    Article  Google Scholar 

  • Gendreau, M., Ghiani, G., & Guerriero, E. (2015). Time-dependent routing problems: A review. Computers and Operations Research, 64, 189–197.

    Article  Google Scholar 

  • Gosavi, A., & Le, V. K. (2022). Maintenance optimization in a digital twin for industry 4.0. Annals of Operations Research. https://doi.org/10.1007/s10479-022-05089-1

    Article  Google Scholar 

  • Gu, Y., Lu, W., Qin, L., Li, M., & Shao, Z. (2019). Short-term prediction of lane-level traffic speeds: A fusion deep learning model. Transportation Research Part C: Emerging Technologies, 106, 1–16.

    Article  Google Scholar 

  • Gupta, S., Modgil, S., Bhattacharyya, S., & Bose, I. (2022). Artificial intelligence for decision support systems in the field of operations research: Review and future scope of research. Annals of Operations Research, 308, 215–274.

    Article  Google Scholar 

  • Hou, Y., Edara, P., & Sun, C. (2015). Traffic flow forecasting for urban work zones. IEEE Transactions on Intelligent Transportation Systems, 16, 1761–1770.

    Article  Google Scholar 

  • Huber, J., Müller, S., Fleischmann, M., & Stuckenschmidt, H. (2019). A data-driven newsvendor problem: From data to decision. European Journal of Operational Research, 278, 904–915.

    Article  Google Scholar 

  • Jiang, C., Bhat, C. R., & Lam, W. H. (2020). A bibliometric overview of transportation research part B: Methodological in the past forty years (1979–2019). Transportation Research Part B: Methodological, 138, 268–291.

    Article  Google Scholar 

  • Ke, J., Zheng, H., Yang, H., & Chen, X. M. (2017). Short-term forecasting of passenger demand under on-demand ride services: A spatio-temporal deep learning approach. Transportation Research Part C: Emerging Technologies, 85, 591–608.

    Article  Google Scholar 

  • Kim, T., Sharda, S., Zhou, X., & Pendyala, R. M. (2020). A stepwise interpretable machine learning framework using linear regression (LR) and long short-term memory (LSTM): City-wide demand-side prediction of yellow taxi and for-hire vehicle (FHV) service. Transportation Research Part C: Emerging Technologies, 120, 102786.

    Article  Google Scholar 

  • Lai, W., Chen, Y., & Sun, E. (2021). Comonotonicity and low volatility effect. Annals of Operations Research, 299, 1057–1099.

    Article  Google Scholar 

  • Lee, K., & Rhee, W. (2022). DDP-GCN: Multi-graph convolutional network for spatiotemporal traffic forecasting. Transportation Research Part C: Emerging Technologies, 134, 103466.

    Article  Google Scholar 

  • Lin, L. I. K. (2000). A note on the concordance correlation coefficient. Biometrics, 56, 324–325.

    Google Scholar 

  • Liu, D., Baldi, S., Yu, W., Cao, J., & Huang, W. (2022). On training traffic predictors via broad learning structures: A benchmark study. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52, 749–758.

    Article  Google Scholar 

  • Ma, T., Zhou, Z., & Antoniou, C. (2018). Dynamic factor model for network traffic state forecast. Transportation Research Part B: Methodological, 118, 281–317.

    Article  Google Scholar 

  • Ma, X., Tao, Z., Wang, Y., Yu, H., & Wang, Y. (2015). Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies, 54, 187–197.

    Article  Google Scholar 

  • Marrekchi, E., Besbes, W., Dhouib, D., & Demir, E. (2021). A review of recent advances in the operations research literature on the green routing problem and its variants. Annals of Operations Research, 304, 529–574.

    Article  Google Scholar 

  • Mena-Oreja, J., & Gozalvez, J. (2020). A comprehensive evaluation of deep learning-based techniques for traffic prediction. IEEE Access, 8, 91188–91212.

    Article  Google Scholar 

  • Nguyen, W. P., & Nof, S. Y. (2020). Strategic lines of collaboration in response to disruption propagation (CRDP) through cyber-physical systems. International Journal of Production Economics, 230, 107865.

    Article  Google Scholar 

  • Park, K. T., Son, Y. H., & Noh, S. D. (2020). The architectural framework of a cyber physical logistics system for digital-twin-based supply chain control. International Journal of Production Research, 59, 1–22.

    Google Scholar 

  • Polson, N. G., & Sokolov, V. O. (2017). Deep learning for short-term traffic flow prediction. Transportation Research Part C: Emerging Technologies, 79, 1–17.

    Article  Google Scholar 

  • Rahmanzadeh, S., Pishvaee, M. S., & Govindan, K. (2023). Emergence of open supply chain management: The role of open innovation in the future smart industry using digital twin network. Annals of Operations Research, 329, 979–1007.

    Article  Google Scholar 

  • Rasheed, A., San, O., & Kvamsdal, T. (2020). Digital twin: Values, challenges and enablers from a modeling perspective. IEEE Access, 8, 21980–22012.

    Article  Google Scholar 

  • Santos, M. J., Curcio, E., Amorim, P., Carvalho, M., & Marques, A. (2021). A bilevel approach for the collaborative transportation planning problem. International Journal of Production Economics, 233, 108004.

    Article  Google Scholar 

  • Shao, H., Lam, W. H., Sumalee, A., Chen, A., & Hazelton, M. L. (2014). Estimation of mean and covariance of peak hour origin-destination demands from day-to-day traffic counts. Transportation Research Part B: Methodological, 68, 52–75.

    Article  Google Scholar 

  • Sharma, K., Dwivedi, Y. K., & Metri, B. (2022). Incorporating causality in energy consumption forecasting using deep neural networks. Annals of Operations Research. https://doi.org/10.1007/s10479-022-04857-3

    Article  Google Scholar 

  • Shaygan, M., Meese, C., Li, W., Zhao, X. G., & Nejad, M. (2022). Traffic prediction using artificial intelligence: Review of recent advances and emerging opportunities. Transportation Research Part C: Emerging Technologies, 145, 103921.

    Article  Google Scholar 

  • Sun, J., & Kim, J. (2021). Joint prediction of next location and travel time from urban vehicle trajectories using long short-term memory neural networks. Transportation Research Part C: Emerging Technologies, 128, 103114.

    Article  Google Scholar 

  • Ting, P. Y., Wada, T., Chiu, Y. L., Sun, M. T., Sakai, K., Ku, W. S., Jeng, A. A. K., & Hwu, J. S. (2020). Freeway travel time prediction using deep hybrid model—Taking Sun Yat-Sen freeway as an example. IEEE Transactions on Vehicular Technology, 69, 8257–8266.

    Article  Google Scholar 

  • Wang, J. (2023). BGcsSENet: Bidirectional GRU with spatial and channel squeeze-excitation network for bundle branch block detection. IEEE Transactions on Human-Machine Systems, 53, 449–457.

    Article  Google Scholar 

  • Wang, J., Zhao, Y., Balamurugan, P., & Selvaraj, P. (2022). Managerial decision support system using an integrated model of Ai and big data analytics. Annals of Operations Research, 326(3), 1–18.

    Google Scholar 

  • Wen, K., Zhao, G., He, B., Ma, J., & Zhang, H. (2022). A decomposition-based forecasting method with transfer learning for railway short-term passenger flow in holidays. Expert Systems with Applications, 189, 116102.

    Article  Google Scholar 

  • Whittle, P. (2007). Networks: Optimisation and evolution. Cambridge University Press.

    Book  Google Scholar 

  • Wu, Y., Tan, H., Qin, L., Ran, B., & Jiang, Z. (2018). A hybrid deep learning based traffic flow prediction method and its understanding. Transportation Research Part C: Emerging Technologies, 90, 166–180.

    Article  Google Scholar 

  • Yao, J., Cheng, Z., & Chen, A. (2023). Bibliometric analysis and systematic literature review of the traffic paradoxes (1968–2022). Transportation Research Part B: Methodological, 177, 102832.

    Article  Google Scholar 

  • Yin, X., Wu, G., Wei, J., Shen, Y., Qi, H., & Yin, B. (2022). Deep learning on traffic prediction: Methods, analysis, and future directions. IEEE Transactions on Intelligent Transportation Systems, 23, 4927–4943.

    Article  Google Scholar 

  • Zheng, Z., Yang, Y., Liu, J., Dai, H. N., & Zhang, Y. (2019). Deep and embedded learning approach for traffic flow prediction in urban informatics. IEEE Transactions on Intelligent Transportation Systems, 20, 3927–3939.

    Article  Google Scholar 

  • Zhou, G., Zhang, C., Li, Z., Ding, K., & Wang, C. (2020). Knowledge-driven digital twin manufacturing cell towards intelligent manufacturing. International Journal of Production Research, 58, 1034–1051.

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the Center for Open Intelligent Connectivity from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education and the National Science and Technology Council (NSTC: 112-2321-B-A49-018, 112-2221-E-A49-049) in Taiwan.

Author information

Authors and Affiliations

  1. Montpellier Business School, Montpellier, France

    Claire Y. T. Chen

  2. KEDGE Business School, Talence, France

    Edward W. Sun

  3. College of AI and College of Computer Science, National Yang Ming Chiao Tung University (NYCU), Hsinchu, Taiwan

    Yi-Bing Lin

  4. Department of Bio Engineering, China Medical University, Taichung, Taiwan

    Yi-Bing Lin

Authors
  1. Claire Y. T. Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Edward W. Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi-Bing Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Edward W. Sun or Yi-Bing Lin.

Ethics declarations

Conflict of interest

Authors declare that they have no Conflict of interest.

Human and/or animal rights

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, C.Y.T., Sun, E.W. & Lin, YB. Reconciling spatiotemporal conjunction with digital twin for sequential travel time prediction and intelligent routing. Ann Oper Res (2024). https://doi.org/10.1007/s10479-024-05990-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10479-024-05990-x

Keywords

Search

Navigation