access icon free Rainfall-integrated traffic speed prediction using deep learning method

© The Institution of Engineering and Technology
Received 10/10/2016, Accepted 28/06/2017, Revised 26/04/2017, Published 03/07/2017

Traffic information prediction is one of the most essential studies for traffic research, operation and management. The successful prediction of traffic speed is increasingly significant for the benefits of both road users and traffic authorities. However, accurate prediction is challenging, due to the stochastic feature of traffic flow and shallow model structure. Furthermore, environmental factors, such as rainfall influence, should also be incorporated to improve accuracy. Inspired by deep learning, this paper investigates the performance of deep belief network (DBN) and long short-term memory (LSTM) to conduct short-term traffic speed prediction with the consideration of rainfall impact as a non-traffic input. The deep learning models have the ability to learn complex features of traffic flow pattern under various rainfall conditions. To validate the performance of rainfall-integrated DBN and LSTM, the traffic detector data from an arterial in Beijing are utilised for model training and testing. The experiment results indicate that with the combination input of speed and additional rainfall data, deep learning models have better prediction accuracy over other existing models, and also yields improvements over the models without rainfall input. Furthermore, the LSTM can outperform the DBN to capture the time-series characteristics of traffic speed data.

Inspec keywords: environmental factors; learning (artificial intelligence); traffic information systems; belief networks; time series

Other keywords: deep belief network; traffic authorities; traffic flow; traffic operation; traffic research; traffic information prediction; shallow model structure; stochastic feature; DBN; LSTM; Beijing; deep training; traffic management; traffic detector data; long short-term memory; environmental factors; rainfall-integrated traffic speed prediction; rainfall influence; deep learning method; deep testing; short-term traffic speed prediction; nontraffic input; road users; time-series characteristics

Subjects: Other topics in statistics; Environmental aspects of computing; Knowledge engineering techniques; Traffic engineering computing

References

    1. 1)
      • 17. Smith, B. L., Demetsky, M. J.: ‘Short-term traffic flow prediction: neural network approach’, Transp. Res. Rec., 1994, 1453, pp. 98–104.
    2. 2)
      • 3. Karlaftis, M. G., Vlahogianni, E. I.: ‘Statistical methods versus neural networks in transportation research: differences, similarities and some insights’, Transp. Res. C, 2011, 19, (3), pp. 387–399.
    3. 3)
      • 35. Ibrahim, A. T., Hall, F. L.: ‘Effects of adverse weather conditions on speed-flow-occupancy relationships’, Transp. Res. Rec., 1994, 1457, pp. 184–191.
    4. 4)
      • 16. Chien, S. I. J., Kuchipudi, C. M.: ‘Dynamic travel time prediction with real-time and historic data’, J. Transp. Eng., 2003, 129, (6), pp. 608–616.
    5. 5)
      • 25. Lingras, P., Sharma, S., Zhong, M.: ‘Prediction of recreational travel using genetically designed regression and time-delay neural network models’, Transp. Res. Rec., 2002, 1805, pp. 16–24.
    6. 6)
      • 8. Ahmed, M. S., Cook, A. R.: ‘Analysis of freeway traffic time-series data by using Box-Jenkins techniques’, Transp. Res. Rec, 1979, 722, pp. 1–9.
    7. 7)
      • 33. Hinton, G. E.: ‘Learning multiple layers of representation’, Trends Cogn. Sci, 2007, 11, (10), pp. 428–434.
    8. 8)
      • 21. Ma, X., Tao, Z., Wang, Y., et al: ‘Long short-term memory neural network for traffic speed prediction using remote microwave sensor data’, Transp. Res. C, 2015, 54, pp. 187–197.
    9. 9)
      • 18. Dougherty, M. S., Cobbett, M. R.: ‘Short-term inter-urban traffic forecasts using neural networks’, Int. J. Forecast., 1997, 13, (1), pp. 21–31.
    10. 10)
      • 14. Chen, H., Grant-Muller, S.: ‘Use of sequential learning for short-term traffic flow forecasting’, Transp. Res. C, 2001, 9, (5), pp. 319–336.
    11. 11)
      • 27. Ishak, S., Kotha, P., Alecsandru, C.: ‘Optimization of dynamic neural network performance for short-term traffic prediction’, Transp. Res. Rec., 2003, 1836, pp. 45–56.
    12. 12)
      • 7. Dunne, S., Ghosh, B.: ‘Weather adaptive traffic prediction using neurowavelet models’, IEEE Trans. Intell. Transp. Syst., 2013, 14, (1), pp. 370–379.
    13. 13)
      • 20. Park, J., Li, D., Murphey, Y. L., et al: ‘Real time vehicle speed prediction using a neural network traffic model’. Proc. 2011 Int. Joint Conf. Neural Networks (IJCNN), San Jose, USA, August 2011, pp. 2991–2996.
    14. 14)
      • 5. Lv, Y., Duan, Y., Kang, W., et al: ‘Traffic flow prediction with big data: a deep learning approach’, IEEE Trans. Intell. Transp. Syst., 2015, 16, (2), pp. 865–873.
    15. 15)
      • 2. Dougherty, M.: ‘A review of neural networks applied to transport’, Transp. Res. C, 1995, 3, (4), pp. 247–260.
    16. 16)
      • 34. Tanner, J. C.: ‘Effect of weather on traffic flow’, Nature, 1952, 4290, p. 107.
    17. 17)
      • 22. Mohamed, A., Dahl, G., Hinton, G.: ‘Deep belief networks for phone recognition’. Proc. NIPS workshop on deep learning for speech recognition and related applications, Vancouver, Canada, December 2009, 1, (9), pp. 1–9.
    18. 18)
      • 38. Agbolosu-Amison, S. J., Sadek, A. W., ElDessouki, W.: ‘Inclement weather and traffic flow at signalized intersections: case study from northern New England’, Transp. Res. Rec., 2004, 1867, pp. 163–171.
    19. 19)
      • 31. Hinton, G. E., Osindero, S., The, Y. W.: ‘A fast learning algorithm for deep belief nets’, Neural Comput., 2006, 18, (7), pp. 1527–1554.
    20. 20)
      • 41. Yuhan, J., Yiman, D., Jianping, W., et al: ‘Impacts of rainfall weather on urban traffic in Beijing: analysis and modeling’. Proc. 94th Transportation Research Board Annual Meeting, Washington, DC, USA, January 2015, pp. 1–13.
    21. 21)
      • 37. Chung, E., Ohtani, O., Warita, H., et al: ‘Does weather affect highway capacity’. Proc. 5th Int. Symp. on Highway Capacity and Quality of Service, Yakoma, Japan, July 2006, pp. 1–8.
    22. 22)
      • 28. van Lint, J. W. C., Hoogendoorn, S. P., van Zuylen, H. J.: ‘Accurate freeway travel time prediction with state-space neural networks under missing data’, Transp. Res. C, 2005, 13, (5), pp. 347–369.
    23. 23)
      • 9. Levin, M., Tsao, Y. D.: ‘On forecasting freeway occupancies and volumes (abridgment)’, Transp. Res. Rec., 1980, 773, pp. 47–49.
    24. 24)
      • 12. Chandra, S. R., Al-Deek, H.: ‘Predictions of freeway traffic speeds and volumes using vector autoregressive models’, J. Intell. Transp. Syst., 2009, 13, (2), pp. 53–72.
    25. 25)
      • 26. Van Lint, J., Hoogendoorn, S., Van Zuylen, H., et al: ‘Freeway travel time prediction with state-space neural networks: modeling state-space dynamics with recurrent neural networks’, Transp. Res. Rec., 2002, 1811, pp. 30–39.
    26. 26)
      • 19. Dia, H.: ‘An object-oriented neural network approach to short-term traffic forecasting’, Eur. J. Oper. Res., 2001, 131, (2), pp. 253–261.
    27. 27)
      • 13. Okutani, I., Stephanedes, Y. J.: ‘Dynamic prediction of traffic volume through Kalman filtering theory’, Transp. Res. B, 1984, 18, (1), pp. 1–11.
    28. 28)
      • 4. Huang, W., Song, G., Hong, H., et al: ‘Deep architecture for traffic flow prediction: deep belief networks with multitask learning’, IEEE Trans. Intell. Transp. Syst., 2014, 15, (5), pp. 2191–2201.
    29. 29)
      • 11. Williams, B. M., Hoel, L. A.: ‘Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results’, J. Transp. Eng., 2003, 129, (6), pp. 664–672.
    30. 30)
      • 1. Vlahogianni, E. I., Karlaftis, M. G., Golias, J. C.: ‘Short-term traffic forecasting: Where we are and where we're going’, Transp. Res. C, 2014, 43, pp. 3–19.
    31. 31)
      • 24. Lee, H., Pham, P., Largman, Y., et al: ‘Unsupervised feature learning for audio classification using convolutional deep belief networks’. Proc. NIPS Advances in Neural Information Processing Systems 22, Vancouver, Canada, December 2009, pp. 1096–1104.
    32. 32)
      • 36. Brilon, W., Ponzlet, M.: ‘Variability of speed-flow relationships on German Autobahns’, Transp. Res. Rec., 1996, 1555, pp. 91–98.
    33. 33)
      • 32. Hinton, G. E.: ‘Training products of experts by minimizing contrastive divergence’, Neural Comput., 2002, 14, (8), pp. 1771–1800.
    34. 34)
      • 40. Akin, D., Sisiopiku, V. P., Skabardonis, A.: ‘Impacts of weather on traffic flow characteristics of urban freeways in Istanbul’, Proc. Soc. Behav. Sci., 2011, 16, pp. 89–99.
    35. 35)
      • 39. Camacho, F. J., García, A., Belda, E.: ‘Analysis of impact of adverse weather on freeway free-flow speed in Spain’, Transp. Res. Rec., 2010, 2168, pp. 150–159.
    36. 36)
      • 23. Nair, V., Hinton, G. E.: ‘3D object recognition with deep belief nets’. Proc. NIPS Advances in Neural Information Processing Systems 22, Vancouver, Canada, December 2009, pp. 1339–1347.
    37. 37)
      • 30. Zhao, Z., Chen, W., Wu, X., et al: ‘LSTM network: a deep learning approach for short-term traffic forecast’, IET Intell. Transp. Syst., 2017, 11, (2), pp. 68–75.
    38. 38)
      • 15. Chen, M., Chien, S.: ‘Dynamic freeway travel-time prediction with probe vehicle data: Link based versus path based’, Transp. Res. Rec., 2001, 1768, pp. 157–161.
    39. 39)
      • 29. Hochreiter, S., Schmidhuber, J.: ‘Long short-term memory’, Neural Comput., 1997, 9, (8), pp. 1735–1780.
    40. 40)
      • 6. Lemieux, J., Ma, Y.: ‘Vehicle speed prediction using seep learning’. Proc. Vehicle Power and Propulsion Conf. (VPPC), Montreal, Canada, October 2015, pp. 1–5.
    41. 41)
      • 10. Van Der Voort, M., Dougherty, M., Watson, S., et al: ‘Combining Kohonen maps with ARIMA time series models to forecast traffic flow’, Transp. Res. C, 1996, 4, (5), pp. 307–318.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2016.0257
Loading

Related content

content/journals/10.1049/iet-its.2016.0257
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading