The use of deep learning methods to predict traffic flow in transportation systems has become a hot research project. The existing predictive model method faces problems such as long calculation time and difficult data pre-processing, especially for the prediction effect of high traffic area. In this study, the authors propose a novel framework ST-ESNet, spatio-temporal expand-and-squeeze networks, that designs several effective strategies for considering the complexity, non-linearity and uncertainty of traffic flow, and better captures traffic flow characteristics to adapt to the dynamic characteristics of traffic trajectory, traffic duration and traffic flow. Specially, we use extend-and-squeeze process rather than squeeze-and-extend process during the normal residual unit to capture farther spatial dependence among regions. Specifically, inverted residual and deformed convolution structures are utilised in the expanding process, and the convolution with stride 2 is utilised in the squeeze process. Furthermore, image feature scaling is used in each residual unit to obtain more fine-grained surface information, which improves the ability of the model to capture dynamic spatial dependence features. Finally, they use stochastic weight averaging to obtain an integration model. In summary, they propose a new predictive model ST-ESNet. The experimental results show that the authors’ proposed network model has better prediction performance compared with the state-of-the-art model.

References

1. 1)
  - 12. 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.
2. 2)
  - 17. Chiou, Y.C., Huang, Y.F.: ‘Stepwise genetic fuzzy logic signal control under mixed traffic conditions’, J. Adv. Trans., 2013, 47, (1), pp. 43–60.
3. 3)
  - 9. Lingras, P., Sharma, S., Zhong, M.: ‘Prediction of recreational travel using genetically designed regression and time-delay neural network models’, Transp. Res. Record J. Transp. Res. Board, 2002, 1805, pp. 16–24.
4. 4)
  - 8. Shuai, M., Xie, K., Pu, W., et al: ‘An online approach based on locally weighted learning for short-term traffic flow prediction’. Proc. of the ACM SIGSPATIAL Int. Conf. on Advances in Geographic Information Systems, Irvine, CA, USA, 2008, pp. 45–53.
5. 5)
  - 21. 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.
6. 6)
  - 15. Srinivasan, D., Choy, M.C., Cheu, R.L.: ‘Neural networks for real-time traffic signal control’, IEEE Trans. Intell. Transp. Syst., 2006, 7, (3), pp. 261–272.
7. 7)
  - 1. Zhang, J., Zheng, Y., Qi, D., et al: ‘DNN-based prediction model for spatio-temporal data’. SIGSPATIAL/GIS, San Francisco, CA, USA, 2016, pp. 92:1–92:4.
8. 8)
  - 33. Garipov, T., Izmailov, P., Podoprikhin, D., et al: ‘Loss surfaces, mode connectivity, and fast ensembling of DNNs’. 2018.
9. 9)
  - 13. El-Tantawy, S., Abdulhai, B., Abdelgawad, H.: ‘Multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (MARLIN-ATSC): methodology and large-scale application on downtown Toronto’, IEEE Trans. Intell. Transp. Syst., 2013, 14, (3), pp. 1140–1150.
10. 10)
  - 32. Huang, G., Li, Y., Pleiss, G., et al: ‘Snapshot ensembles: train 1, get M for free’. 2017.
11. 11)
  - 18. Bi, Y., Srinivasan, D., Lu, X., et al: ‘Type-2 fuzzy multi-intersection traffic signal control with differential evolution optimization’, Expert Syst. Appl., 2014, 41, (16), pp. 7338–7349.
12. 12)
  - 6. Li, K.-L., Zhai, C.-J., Xu, J.-M.: ‘Short-term traffic flow prediction using a methodology based on arima and RBN-ANN’. Proc. of the Chinese Automation Congress, Jinan, People's Republic of China, 2017, pp. 2804–2807.
13. 13)
  - 7. Castro-Neto, M., Jeong, Y.-S., Jeong, M.-K., et al: ‘Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions’, Expert Syst. Appl., 2009, 36, (3), pp. 6164–6173.
14. 14)
  - 26. Long, J., Shelhamer, E., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’. Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431–3440.
15. 15)
  - 20. Hu, W., Wang, H., Du, B., et al: ‘A multi-intersection model and signal timing plan algorithm for urban traffic signal control’, Transport, 2014, 32, (4), pp. 1–11.
16. 16)
  - 2. Zhang, J., Zheng, Y., Qi, D.: ‘Deep spatio-temporal residual networks for citywide crowd flows prediction’. AAAI, San Francisco, CA, USA, 2017, pp. 1655–1661.
17. 17)
  - 25. Zhu, J., Fang, L., Ghamisi, P.: ‘Deformable convolutional neural networks for hyperspectral image classification’, IEEE Geosci. Remote Sens. Lett., 2018, 15, (8), pp. 1254–1258.
18. 18)
  - 23. Xue, Z., Xue, Y.: ‘Multi long-short term memory models for short term traffic flow prediction’, IEICE Trans., 2018, 101-D, (12), pp. 3272–3275.
19. 19)
  - 22. Yang, H.F., Dillon, T.S., Chen, Y.P.P.: ‘Optimized structure of the traffic flow forecasting model with a deep learning approach’, IEEE Trans. Neural Netw. Learn. Syst., 2017, 28, (10), pp. 2371–2381.
20. 20)
  - 3. Voort, M.V.D., Dougherty, M., Watson, S.: ‘Combining Kohonen maps with arima time series models to forecast traffic flow’, Transp. Res. C, Emerg. Technol., 1996, 4, (5), pp. 307–318.
21. 21)
  - 4. Huang, D., Deng, Z., Zhao, L., et al: ‘A short-term traffic flow forecasting method based on Markov chain and grey Verhulst model’. Proc. of the Data Driven Control and Learning Systems, Chongqing, People's Republic of China, 2017, pp. 606–610.
22. 22)
  - 11. Vlahogianni, E.E.I.., Karlaftis, M.G., Golias, J.C.: ‘Spatio-temporal short-term urban traffic volume forecasting using genetically optimized modular networks’, Comput.-Aided Civ. Infrastruct. Eng., 2010, 22, (5), pp. 317–325.
23. 23)
  - 28. Robbins, H., Monro, S.: ‘A stochastic approximation method’, Ann. Math. Stat., 1951, 22, (3), pp. 400–407.
24. 24)
  - 14. Jin, J., Ma, X.: ‘A group-based traffic signal control with adaptive learning ability’, Eng. Appl. Artif. Intell., 2017, 65, pp. 282–293.
25. 25)
  - 10. Hochreiter, S., Schmidhuber, J.: ‘Long short-term memory’, Neural Comput., 1997, 9, (8), pp. 1735–1780.
26. 26)
  - 30. Izmailov, P., Podoprikhin, D., Garipov, T., et al: ‘Averaging weights leads to wider optima and better generalization’. UAI, Monterey, CA, USA, 2018, pp. 876–885.
27. 27)
  - 16. Chao, K.H., Lee, R.H., Wang, M.H.: ‘An intelligent traffic light control based on extension neural network’. Int. Conf. Knowledge-based Intelligent Information & Engineering Systems, Berlin, Germany, 2008, pp. 17–24.
28. 28)
  - 27. Lin, T.-Y., Dollár, P., Girshick, R.B., et al: ‘Feature pyramid networks for object detection’. CVPR, Honolulu, HI, USA, 2017, pp. 936–944.
29. 29)
  - 19. Hu, W., Wang, H., Yan, L., et al: ‘A swarm intelligent method for traffic light scheduling: application to real urban traffic networks’, Appl. Intell., 2016, 44, (1), pp. 208–231.
30. 30)
  - 34. Dozat, T.: ‘Incorporating Nesterov momentum into Adam’. ICLR Workshop 2013–16, San Juan, PR, USA, 2016.
31. 31)
  - 29. Kingma, D.P., Ba, J.L.: ‘Adam: a method for stochastic optimization’. Int. Conf. on Learning Representations, ICLR, San Diego, CA, USA, 2015.
32. 32)
  - 24. Sandler, M., Howard, A.G., Zhu, M., et al: ‘Mobilenetv2: inverted residuals and linear bottlenecks’. CVPR, Salt Lake City, UT, USA, 2018, pp. 4510–4520.
33. 33)
  - 31. Zeiler, M.D., Taylor, G.W., Fergus, R.: ‘Adaptive deconvolutional networks for mid and high level feature learning’. ICCV, Barcelona, Spain, 2011, pp. 2018–2025.
34. 34)
  - 5. Lippi, M., Bertini, M., Frasconi, P.: ‘Collective traffic forecasting’. Proc. of the Joint European Conf. on Machine Learning and Knowledge Discovery in Databases, Berlin, Germany, 2010, pp. 259–273.

Spatio-temporal expand-and-squeeze networks for crowd flow prediction in metropolis

References

Related content