A Learning-Based Multimodel Integrated Framework for Dynamic Traffic Flow Forecasting

  • Teng Zhou
  • Guoqiang Han
  • Xuemiao Xu
  • Chu Han
  • Yuchang Huang
  • Jing Qin


Accurate and timely traffic flow forecasting is essential for many intelligent transportation systems. However, it is quite challenging to develop an efficient and robust forecasting model due to the inherent randomness and large variations of traffic flow. Over the past two decades, a variety of traffic flow forecasting models have been proposed. While each model has its merits and can achieve satisfactory forecasting results under certain traffic conditions, it is difficult for a single model to deal with various conditions well. In this paper, we proposed a novel deep learning-based multimodel integration framework in order to overcome the limitations of previous methods in dealing with large variations and uncertainties of traffic flow and hence improve the forecasting accuracy. Our framework can dynamically choose an optimal model or an optimal subset of models from a set of candidate models to forecast the future traffic flow conditions according to current input data. We employ stacked autoencoder (SAE), a simple yet efficient deep learning architecture, to extract the implicit relationships hidden in the traffic flow data and employed labeled data to fine tune the parameters of the architecture. Compared with the hand-crafted features and explicable dependence relations leveraged in previous models, the features learning from SAE are more representative and hence have more powerful forecasting capability. In addition, we propose a model-driven scheme to automatically label the training data and develop three strategies to integrate multiple models. Extensive experiments performed on three typical traffic flow datasets demonstrate the proposed framework outperforms state-of-the-art models and achieves much more accurate forecasting results under large and sudden variations.


Traffic flow forecasting Stacked autoencoder Multimodel integration Variation and uncertainty Deep learning 



This work was supported partially by the National Natural Science Foundation of China (Nos. 61472145, 61772206, U1611461), in part by Special Fund of Science and Technology Research and Development on Application From Guangdong Province(SF-STRDA-GD No. 2016B010124011), in part by Guangdong High-level personnel of special support program (No. 2016TQ03X319) and the Guangdong Natural Science Foundation (No. 2017A030311027, No. 2016A030313047). The authors would like to thank Dr. Yubin Wang, from SIM Industries, Sassenheim, Netherlands, who provides the careful collected and preprocessed traffic flow data from the motorways of Amsterdam.


  1. 1.
    Agarwal M, Maze TH, Souleyrette R (2005) Impacts of weather on urban freeway traffic flow characteristics and facility capacity. Transp Res Symp Mid-Cont 20(5):1121–1134Google Scholar
  2. 2.
    Ahmed MS, Cook AR (1979) Analysis of freeway traffic time-series data by using Box–Jenkins techniques. 722, Transportation Research Record, WashingtonGoogle Scholar
  3. 3.
    Ahmed SA, Cook AR (1982) Discrete dynamic models for freeway incident detection systems. Transp Plan Technol 7(4):231–242CrossRefGoogle Scholar
  4. 4.
    Akata Z, Perronnin F, Harchaoui Z, Schmid C (2014) Good practice in large-scale learning for image classification. IEEE Trans Pattern Anal Mach Intell 36(3):507–520CrossRefGoogle Scholar
  5. 5.
    Barimani N, Kian AR, Moshiri B (2014) Real time adaptive non-linear estimator/predictor design for traffic systems with inadequate detectors. Intell Transp Syst IET 8(3):308–321CrossRefGoogle Scholar
  6. 6.
    Basu S, Karki M, Ganguly S, DiBiano R, Mukhopadhyay S, Nemani R (2015) Learning sparse feature representations using probabilistic quadtrees and deep belief nets. In: European symposium on artificial neural networks, ESANN, pp 367–375Google Scholar
  7. 7.
    Bhavathrathan B, Patil GR (2013) Analysis of worst case stochastic link capacity degradation to aid assessment of transportation network reliability. Procedia Soc Behav Sci 104(Supplement C):507–515CrossRefGoogle Scholar
  8. 8.
    Bohlin T (1976) Four cases of identification of changing systems. Math Sci Eng 126:441–518CrossRefGoogle Scholar
  9. 9.
    Boto-Giralda D, Díaz-Pernas FJ, González-Ortega D, Díez-Higuera JF, Antón-Rodríguez M, Martínez-Zarzuela M, Torre-Díez I (2010) Wavelet-based denoising for traffic volume time series forecasting with self-organizing neural networks. Comput Aided Civ Infrastruct Eng 25(7):530–545CrossRefGoogle Scholar
  10. 10.
    Chan KY, Dillon TS, Singh J, Chang E (2012) Neural-network-based models for short-term traffic flow forecasting using a hybrid exponential smoothing and Levenberg–Marquardt algorithm. IEEE Trans Intell Transp Syst 13(2):644–654CrossRefGoogle Scholar
  11. 11.
    Comert G, Bezuglov A (2013) An online change-point-based model for traffic parameter prediction. IEEE Trans Intell Transp Syst 14(3):1360–1369CrossRefGoogle Scholar
  12. 12.
    Davarynejad M, Wang Y, Vrancken J, van den Berg J (2011) Multi-phase time series models for motorway flow forecasting. In: 2011 14th international IEEE conference on intelligent transportation systems (ITSC). IEEE, pp 2033–2038Google Scholar
  13. 13.
    Davis GA, Nihan NL (1991) Nonparametric regression and short-term freeway traffic forecasting. J Transp Eng 117:178–188CrossRefGoogle Scholar
  14. 14.
    Dou Q, Chen H, Yu L, Zhao L, Qin J, Wang D, Mok VC, Shi L, Heng PA (2016) Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks. IEEE Trans Med Imaging 35(5):1182–1195CrossRefGoogle Scholar
  15. 15.
    Ghosh B, Basu B, O’Mahony M (2009) Multivariate short-term traffic flow forecasting using time-series analysis. IEEE Trans Intell Transp Syst 10(2):246–254CrossRefGoogle Scholar
  16. 16.
    Guo J, Huang W, Williams BM (2014) Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification. Transp Res Part C Emerg Technol 43:50–64CrossRefGoogle Scholar
  17. 17.
    Hamed MM, Al-Masaeid HR, Said ZMB (1995) Short-term prediction of traffic volume in urban arterials. J Transp Eng 121(3):249–254CrossRefGoogle Scholar
  18. 18.
    Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Hong WC, Pai PF, Yang SL, Theng R (2006) Highway traffic forecasting by support vector regression model with tabu search algorithms. In: International joint conference on neural networks, 2006, IJCNN’06. IEEE, pp 1617–1621Google Scholar
  20. 20.
    Hong WC, Dong Y, Zheng F, Lai CY (2011) Forecasting urban traffic flow by SVR with continuous ACO. Appl Math Model 35(3):1282–1291MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Hu W, Yan L, Liu K, Wang H (2015) A short-term traffic flow forecasting method based on the hybrid PSO-SVR. Neural Process Lett 43:155–172CrossRefGoogle Scholar
  22. 22.
    Huang W, Song G, Hong H, Xie K (2014) Deep architecture for traffic flow prediction: deep belief networks with multitask learning. IEEE Trans Intell Transp Syst 15(5):2191–2201CrossRefGoogle Scholar
  23. 23.
    Jeong YS, Byon YJ, Mendonca Castro-Neto M, Easa SM (2013) Supervised weighting-online learning algorithm for short-term traffic flow prediction. IEEE Trans Intell Transp Syst 14(4):1700–1707CrossRefGoogle Scholar
  24. 24.
    Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093
  25. 25.
    Kumar K, Jain V (1999) Autoregressive integrated moving averages (ARIMA) modelling of a traffic noise time series. Appl Acoust 58(3):283–294MathSciNetCrossRefGoogle Scholar
  26. 26.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  27. 27.
    Levin M, Tsao YD (1980) On forecasting freeway occupancies and volumes. J Transp Res Rec 773:47–49Google Scholar
  28. 28.
    Lippi M, Bertini M, Frasconi P (2013) Short-term traffic flow forecasting: an experimental comparison of time-series analysis and supervised learning. IEEE Trans Intell Transp Syst 14(2):871–882CrossRefGoogle Scholar
  29. 29.
    Liu DC, Nocedal J (1989) On the limited memory BFGS method for large scale optimization. Math Program 45(1–3):503–528MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    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):865–873Google Scholar
  31. 31.
    Maria J, Amaro J, Falcao G, Alexandre LA (2016) Stacked autoencoders using low-power accelerated architectures for object recognition in autonomous systems. Neural Process Lett 43(2):445–458CrossRefGoogle Scholar
  32. 32.
    Mathew TV, Rao KVK (2007) Introduction to transportation engineering. National Programme on Technology Enhanced Learning, PowaiGoogle Scholar
  33. 33.
    Messer CJ (1993) Advanced freeway system ramp metering strategies for Texas. Technical report, Texas Transportation Institute, TexasGoogle Scholar
  34. 34.
    Moayedi HZ, Masnadi-Shirazi M (2008) ARIMA model for network traffic prediction and anomaly detection. In: International symposium on information technology, 2008. ITSim 2008, vol 4. IEEE, pp 1–6Google Scholar
  35. 35.
    Mori U, Mendiburu A, lvarez M, Lozano JA (2015) A review of travel time estimation and forecasting for advanced traveller information systems. Transportmetrica A Transp Sci 11(2):119–157. CrossRefGoogle Scholar
  36. 36.
    Okutani I, Stephanedes YJ (1984) Dynamic prediction of traffic volume through Kalman filtering theory. Transp Res Part B Methodol 18(1):1–11CrossRefGoogle Scholar
  37. 37.
    Pan T, Sumalee A, Zhong RX, Indra-Payoong N (2013) Short-term traffic state prediction based on temporal-spatial correlation. IEEE Trans Intell Transp Syst 14(3):1242–1254CrossRefGoogle Scholar
  38. 38.
    Peng Y, Lei M, Li JB, Peng XY (2014) A novel hybridization of echo state networks and multiplicative seasonal ARIMA model for mobile communication traffic series forecasting. Neural Comput Appl 24(3–4):883–890CrossRefGoogle Scholar
  39. 39.
    Ross P (1982) Exponential filtering of traffic data. 869, Transportation Research Board, WashingtonGoogle Scholar
  40. 40.
    Singh K, Li B (2012) Estimation of traffic densities for multilane roadways using a Markov model approach. IEEE Trans Ind Electron 59(11):4369–4376CrossRefGoogle Scholar
  41. 41.
    Smith BL, Demetsky MJ (1994) Short-term traffic flow prediction: neural network approach. J Transp Res Rec 1453:98–104Google Scholar
  42. 42.
    Smith BL, Demetsky MJ (1997) Traffic flow forecasting: comparison of modeling approaches. J Transp Eng 123(4):261–266CrossRefGoogle Scholar
  43. 43.
    Srivastava N (2013) Improving neural networks with dropout. PhD thesis, University of TorontoGoogle Scholar
  44. 44.
    Stephanedes YJ, Michalopoulos PG, Plum RA (1981) Improved estimation of traffic flow for real-time control. J Transp Res Rec 795:28–39Google Scholar
  45. 45.
    Sumalee A, Zhong R, Pan T, Szeto W (2011) Stochastic cell transmission model (SCTM): a stochastic dynamic traffic model for traffic state surveillance and assignment. Transp Res Part B Methodol 45(3):507–533CrossRefGoogle Scholar
  46. 46.
    Szeto MW, Gazis DC (1972) Application of Kalman filtering to the surveillance and control of traffic systems. Transp Sci 6(4):419–439CrossRefGoogle Scholar
  47. 47.
    Tchrakian TT, Basu B, O’Mahony M (2012) Real-time traffic flow forecasting using spectral analysis. IEEE Trans Intell Transp Syst 13(2):519–526CrossRefGoogle Scholar
  48. 48.
    Tomczak JM (2015) Learning informative features from restricted Boltzmann machines. Neural Process Lett pp 1–16Google Scholar
  49. 49.
    Tomczak JM, Gonczarek A (2016) Learning invariant features using subspace restricted Boltzmann machine. Neural Process Lett 45:173–182CrossRefGoogle Scholar
  50. 50.
    Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning, ACM, pp 1096–1103Google Scholar
  51. 51.
    van Hinsbergen CP, Schreiter T, Zuurbier FS, Van Lint J, van Zuylen HJ (2012) Localized extended Kalman filter for scalable real-time traffic state estimation. IEEE Trans Intell Transp Syst 13(1):385–394CrossRefGoogle Scholar
  52. 52.
    Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol PA (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11:3371–3408MathSciNetzbMATHGoogle Scholar
  53. 53.
    Vlahogianni EI, Karlaftis MG, Golias JC (2005) Optimized and meta-optimized neural networks for short-term traffic flow prediction: a genetic approach. Transp Res Part C Emerg Technol 13(3):211–234CrossRefGoogle Scholar
  54. 54.
    Wang Y, van Schuppen JH, Vrancken J (2014) Prediction of traffic flow at the boundary of a motorway network. IEEE Trans Intell Transp Syst 15(1):214–227CrossRefGoogle Scholar
  55. 55.
    Wang Y, Cheng JZ, Ni D, Lin M, Qin J, Luo X, Xu M, Xie X, Heng PA (2016) Towards personalized statistical deformable model and hybrid point matching for robust MR-TRUS registration. IEEE Trans Med Imaging 35(2):589–604CrossRefGoogle Scholar
  56. 56.
    Williams BM, Hoel LA (2003) Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J Transp Eng 129(6):664–672CrossRefGoogle Scholar
  57. 57.
    Williams BM, Durvasula PK, Brown DE (1998) Urban freeway traffic flow prediction: application of seasonal autoregressive integrated moving average and exponential smoothing models. Transp Res Rec J Transp Res Board 1644(1):132–141CrossRefGoogle Scholar
  58. 58.
    Xie Y, Zhang Y, Ye Z (2007) Short-term traffic volume forecasting using Kalman filter with discrete wavelet decomposition. Comput Aided Civ Infrastruct Eng 22(5):326–334CrossRefGoogle Scholar
  59. 59.
    Yuan Y, Van Lint J, Wilson RE, van Wageningen-Kessels F, Hoogendoorn SP (2012) Real-time Lagrangian traffic state estimator for freeways. IEEE Trans Intell Transp Syst 13(1):59–70CrossRefGoogle Scholar
  60. 60.
    Zhou T, Han G, Xu X, Lin Z, Han C, Huang Y, Qin J (2017) \(\delta \)-agree AdaBoost stacked autoencoder for short-term traffic flow forecasting. Neurocomputing 247:31–38. CrossRefGoogle Scholar
  61. 61.
    Zhu JZ, Cao JX, Zhu Y (2014) Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections. Transp Res Part C Emerg Technol 47:139–154CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Teng Zhou
    • 1
  • Guoqiang Han
    • 2
  • Xuemiao Xu
    • 2
  • Chu Han
    • 3
  • Yuchang Huang
    • 4
  • Jing Qin
    • 5
  1. 1.Department of Computer Science, College of EngineeringShantou UniversityShantouChina
  2. 2.School of Computer Science and EngineeringSouth China University of TechnologyGuangzhouChina
  3. 3.Department of Computer Science and EngineeringThe Chinese University of Hong KongSha TinHong Kong
  4. 4.College of Mathematics and InformationSouth China Agricultural UniversityGuangzhouChina
  5. 5.Center for Smart Health, School of NursingThe Hong Kong Polytechnic UniversityKowloonHong Kong

Personalised recommendations