Skip to main content
SpringerLink
Log in

A deep learning-based framework for road traffic prediction

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Due to the exponential rise in the number of vehicles and road segments in cities, traffic prediction becomes more difficult, necessitating the application of sophisticated algorithms such as deep learning (DL). The models used in the literature provide accurate predictions for specific cases when the data flow is properly prepared. However, in complex situations, these approaches fail, and thus, the prediction must be developed through a process rather than a prediction calculation method. In addition to using a pure and robust DL prediction model, an efficient approach could be built by taking into account two other factors, namely the relationships between road segments and the amount and quality of the training data. The main goal of our research is to develop a three-stage framework for road traffic prediction based on statistical and deep learning modules. First, a cross-correlation prediction with a Long Short-Term Memory model (LSTM) is implemented to predict the influential road segments; second, a deep generative model (DGM)-based data augmentation is used to improve the data of the related segments; and third, we adapt a Neural Basis Expansion Analysis for interpretable Time Series (N-BEATS) architecture, to the resulting data to implement the prediction module. The framework components are trained and validated using the 6th Beijing road traffic dataset.

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Data availability

The dataset used is requested from Baidu Research dataset repository that has committed to provide a datasets at no cost for research uses. The detailed preprocessing of this sub-dataset is described in the paper https://doi.org/10.48550/arXiv.1806.07380.

References

  1. Aaron V, Sander D, Heiga Z, Karen S, Oriol V, Alex G, Nal K, Andrew S, Koray K (2016) WaveNet: a generative model for raw audio. In: International Conference on Learning Representations

  2. Alarcon-Aquino A, Barria JA (2006) Multiresolution FIR neural-network-based learning algorithm applied to network traffic prediction. IEEE Trans Syst Man Cybern 2006 Part C (Appl Rev) 36(2):208–220

    Article  Google Scholar 

  3. Alexander A, Konstantinos B, Michael B, Valentin F, Jan G, Tim J, Maddix D, Rangapuram S, Salinas D, Schulz J (2020) Gluonts: probabilistic and neural time series modeling in python

  4. Alzantot M, Supriyo C, Mani S (2017) A deep learning architecture for synthetic sensor data generation. In: 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE, pp 188–193

  5. Ashish V, Shazeer N, Parmar N, Uszkoreit J, Jones L (2017) Attention is all you need. In: NeurIPS

  6. Baidu research Open-Access dataset. Available online www.ai.baidu.com

  7. Baofeng D, Kai S, Kaishan Z, Xiaoxi H (2016) Long-term correlations and multifractality of traffic flow measured by GIS for congested and free-flow roads. Fractals 24(1):1650012

    Article  Google Scholar 

  8. Billy M, Williams M, Lester A, Hoel F (2003) Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J Transp Eng 129(6):664–672

    Article  Google Scholar 

  9. Bucur L, Florea A, Petrescu B (2010) An adaptive fuzzy neural network for traffic prediction, control and automation (MED). In: 18th Mediterranean Conference on Control and Automation 2010, MED’10

  10. Chan KY, Dillon TS (2012) On-road sensor configuration design for traffic flow prediction using fuzzy neural networks and Taguchi method. IEEE Trans Ind Inform 8(2):255–266

    Article  Google Scholar 

  11. Cheng T, James H (2011) Spatio-temporal autocorrelation of road network data. J Geogr Syst 14(4):1–25

    Google Scholar 

  12. Cristobal E, Stephanie L, Gunnar R (2017) Real-valued (medical) time series generation with recurrent conditional GANs. arXiv:1706.02633

  13. Fei S, Honghui D, Limin J, Zhao T, Xuan S (2016) Space-time correlation analysis of traffic flow on road network. Int J Mod Phys B 31(05):1750027

    MathSciNet  Google Scholar 

  14. Fred B, Paul R (1995) Principal-components analysis and exploratory and confirmatory factor analysis. American Psychological Association, Washington DC, pp 99–136

    Google Scholar 

  15. Goodfellow I, Jean P, Mehdi M, Bing X, David W, Sherjil O, Aaron C, Yoshua B (2014) Generative adversarial networks. Adv Neural Inf Process Syst 3(11)

  16. Guillermo I, Talavera E, González-Prieto A, Alberto MA, Gámez-Canaval S (2023) Data augmentation techniques in time series domain: a survey and taxonomy. Springer, Berlin

    Google Scholar 

  17. Guoqiang Y, Jianming H, Changshui Z, Like Z, Jingyan S (2003) Short-term traffic flow forecasting based on Markov chain model. In: Intelligent Vehicles Symposium 2003, Proceedings. IEEE

  18. Guoqiang Y, Changshui Z (1988) Switching ARIMA model based forecasting for traffic flow. In: International Conference on Acoustics, Speech, and Signal Processing 2004, ICASSP-88, vol 2, pp ii–429-32

  19. Haiyang Y, Zhihai W, Shuqin W, Yunpeng W, Xiaolei M (2017) Spatio-temporal recurrent convolutional networks for traffic prediction in transportation network. Sensors 27(17):1501

    Google Scholar 

  20. Hauke J, Tomasz K (2011) Comparison of values of Pearson’s and Spearman’s correlation coefficients on the same sets of data. Quaestiones Geographicae 30(2):87–93

    Article  Google Scholar 

  21. Honghui D, Limin J, Xiaoliang S, Chenxi L, Yong Q (2009) Road traffic flow prediction with a time-oriented ARIMA model. In: International Conference on Digital Content, Multimedia Technology and its Applications 2009, Seoul

  22. Jinsung Y, Daniel J, Mihaela V (2019) Time-series generative adversarial networks. In: Conference: Neural Information Processing Systems 2019

  23. Kai S, Baofeng D, Kaishan Z, Chaoyang F, Laurence, S (2017) Detrended cross-correlation analysis of urban traffic congestion and NO2 concentrations in Chengdu. Transp Res Part D Transp Environ 61

  24. Kumar K, Parida M, Katiyar VK (2017) Short term traffic flow prediction in heterogeneous condition using artificial neural network. Transp J 30(4)

  25. Laurens V, Geoffrey H (2008) Visualizing data using t-SNE. J Mach Learn Res 9(2605):2579–2605

    Google Scholar 

  26. Lele Z, Callum S, Samithree R, Gentry W, Timothy A, GaroniTimothy G (2017) Study of cross-correlations in traffic networks with applications to perimeter control. Transp Res Rec J Transp Res Board 2623(1):108–116

    Article  Google Scholar 

  27. Ling Z, Yujiao S, Chao Z, Yu L, Pu W, Tao L, Min D, Haifeng L (2019) T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst 21(9):3848–3858

    Google Scholar 

  28. Lingli L, Hongxia X (2013) Traffic prediction based on SVM training sample divided by time. TELKOMNIKA Indone J Electr Eng 11(12)

  29. Lizhen W, Chun K, Xiaohong H, Wei C (2020) A short-term load forecasting method based on GRU-CNN hybrid neural network model. Math Probl Eng

  30. Luca S (2018) Generating spiking time series with generative adversarial networks: an application on banking transactions

  31. Lv Y, Duan Y, Kang W, Li Z, Wang FY (2015) Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transp Syst 16(2):865–873

    Google Scholar 

  32. Miaomiao C, Li V, Vincent C (2020) A CNN-LSTM model for traffic speed prediction. In: IEEE 91st Vehicular Technology Conference 2020 (VTC2020-Spring)

  33. Min W, Wynter L (2011) Real-time road traffic prediction with spatio-temporal correlations. Transp Res Part C Emerg Technol 19(4):606–616

    Article  Google Scholar 

  34. Mohamed S, Ahmed A (2014) Analysis of freeway traffic time-series data by using box-Jenkins technique. J Transp Technol 4(1)

  35. Yuan EX, Congwen Z, Juerg L (2016) A novel way to detect correlations on multi-time scales, with temporal evolution and for multi-variables. Sci Rep 6(1):27707

    Article  ADS  CAS  PubMed  PubMed Central  Google Scholar 

  36. Navin R, Sovit B, Hong PZ, Hoon K (2020) City-wide traffic congestion prediction based on CNN, LSTM and transpose CNN. IEEE Access

  37. Olof M (2016) C-RNN-GAN: continuous recurrent neural networks with adversarial training. arXiv preprint arXiv:1611.09904

  38. Oreshkin BN, Carpov D, Chapados N, Bengio Y (2020) N-BEATS: neural basis expansion analysis for interpretable time series forecasting. In: International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia

  39. Pan TL, Sumalee A, Zhong RX, Payoong NI (2013) Short-term traffic state prediction based on temporal-spatial correlation. IEEE Trans Intell Transp Syst 14(3):1242

    Article  Google Scholar 

  40. Qi Y, Ishak S (2014) A Hidden Markov Model for short term prediction of traffic conditions on free-ways. Transp Res Part C Emerg TechnolPart 43:95–111

    Article  Google Scholar 

  41. Qinghua D, Xue B, Tingting Z, Yi Z, Yu Z, Shumin F (2011) Spatial cross correlations of traffic flows on urban road networks. J Tsinghua Univ 51(3):313–317

    Google Scholar 

  42. Qingsong W, Liang S, Fan Y, Xiaomin S, Jingkun G, Xue W, Huan X (2021) Time series data augmentation for deep learning: a survey. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 2021, Survey Track, pp 4653–4660

  43. Shangyu S, Huayi W, Longgang X (2020) City-wide traffic flow forecasting using a deep convolutional neural network. Sensor

  44. Shaokun Z, Zejian K, Zhiyou H, Zhemin Z, Cheng W, Jonathan L (2018) Traffic prediction based on cascade artificial neural network. In: IGARSS 2018—IEEE International Geoscience and Remote Sensing Symposium

  45. Shengdong D, Tianrui L, Xun G, Shi-Jinn H (2018) A hybrid method for traffic flow forecasting using multimodal deep learning. Int J Comput Intell Syst 13(1)

  46. Shengmin G, Dong Z, Jingfang F, Qingfeng T, Tongyu Z, Weifeng T, Daqing L, Shlomo H (2019) Identifying the most influential roads based on traffic correlation networks. EPJ Data Sci 8(1)

  47. Shota H, Hideaki H, Seiichi U (2018) Biosignal data augmentation based on generative adversarial networks. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, pp 368–371

  48. Solomatine D, See LM, Abrahart RJ (2008) Data-driven modelling: concepts, approaches and experiences. Practical Hydroinformatics 68:17–30

    Article  Google Scholar 

  49. SweeKiat L, YiLoo N, NgaiMan C, Gemma R, Yuval E (2018) DOPING: generative data augmentation for unsupervised anomaly detection with GAN. In: IEEE International Conference on Data Mining (ICDM)

  50. Vasantha K, Lelitha V (2015) Short-term traffic flow prediction using seasonal ARIMA model with limited input data. Eur Transp Res Rev 7:Article number: 21

  51. Vlahogianni EI, Karlaftis MG (2013) Fuzzy-entropy neural network freeway incident duration modeling with single and competing uncertainties. Comput Aided Civ Infrastruct Eng 28(6):420–433

    Article  Google Scholar 

  52. Wang J, Deng W, Guo Y (2014) New Bayesian combination method for short-term traffic flow forecasting. Transp Res Part C Emerg Technol 43:79–94

    Article  CAS  Google Scholar 

  53. Wangyang W, Honghai W, Huadong M (2019) An AutoEncoder and LSTM-based traffic flow prediction method. Sensors 19(13)

  54. Wenqi L, Yikang R, Bin R (2020) Lane-level traffic speed forecasting: a novel mixed deep learning model. IEEE Trans Intell Transp Syst 23(4):3601–3612

    ADS  Google Scholar 

  55. William BM, Durvasula PK, Brown DE (1998) Urban freeway travel prediction: application of seasonal ARIMA and exponential smoothing models. Transp Res Rec J Transp Res Board 1644(1):132–141

    Article  Google Scholar 

  56. Xinqiang C, Shubo W, Chaojian S, Yanguo H, Yongsheng Y, Ruimin K, Jiansen Z (2020) Sensing data supported traffic flow prediction via denoising schemes and ANN: a comparison. IEEE Sens J 20(23):14317–14328

    Article  Google Scholar 

  57. Xingyuan D, Rui F, Yilun L, Fei-Yue W, Fellow F, Li L (2017) DeepTrend: a deep hierarchical neural network for traffic flow prediction. Mach Learn

  58. Yanguang C (2015) A new methodology of spatial cross-correlation analysis. PLoS ONE 10(5):e0126158

    Article  Google Scholar 

  59. Yizhe Z, Zhe G, C. (2016) Generating text via adversarial training. In: NIPS Workshop on Adversarial Training, vol 21

  60. Wu Y, Tan H (2016) Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework. Comput Vis Pattern Recognit

  61. Zaiyue Z, Cungen C (2015) Road traffic freight volume forecast using support vector machine combining forecasting. J Softw 6(9):1680–1687

    Google Scholar 

Download references

Funding

This research was developed in an academic context. The authors declare that no funding is provided for this research.

Author information

Authors and Affiliations

  1. Ecole Militaire Polytechnique, PO Box 17, Bordj El Bahri, Algiers, Algeria

    Redouane Benabdallah Benarmas & Kadda Beghdad Bey

Authors
  1. Redouane Benabdallah Benarmas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kadda Beghdad Bey
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization was contributed by R.B; K.B. Methodology was contributed by R.B; K.B. Data visualization was contributed by R.B. Writing—original draft, was contributed by R.B. All authors approved the final submitted draft.

Corresponding author

Correspondence to Redouane Benabdallah Benarmas.

Ethics declarations

Conflict of interest

The authors declare no competing interests exist.

Ethical approval

All authors have been personally and actively involved in substantial work leading to the paper and will take public responsibility for its content

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

Benabdallah Benarmas, R., Beghdad Bey, K. A deep learning-based framework for road traffic prediction. J Supercomput 80, 6891–6916 (2024). https://doi.org/10.1007/s11227-023-05718-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-023-05718-x

Keywords

Search

Navigation