Skip to main content

Advertisement

SpringerLink
Log in

Attention-based Conv-LSTM and Bi-LSTM networks for large-scale traffic speed prediction

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

Abstract

Timely and accurate traffic speed prediction has gained increasing importance for urban traffic management and helping one to make advisable travel decision. However, the existing approaches have difficulty extracting features of large-scale traffic data. This study proposed a hybrid deep learning method named AB-ConvLSTM for large-scale traffic speed prediction. The proposed model consists of a convolutional-long short-term memory (Conv-LSTM) module, an attention mechanism module, and two bidirectional LSTM (Bi-LSTM) modules. Conv-LSTM networks are used to extract the spatiotemporal features of traffic speed data. In addition, the attention mechanism module is introduced to enhance the performance of Conv-LSTM by automatically capturing the importance of different historical periods to the final prediction and assigning corresponding weights. What's more, two Bi-LSTM networks are designed to extract daily and weekly periodic features and capture variation tendency from forward and backward traffic data. Experimental results carried out on urban road networks show that the proposed model consistently outperforms the competing models.

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

References

  1. Mackenzie J, Roddick JF, Zito R (2019) An evaluation of HTM and LSTM for short-term arterial traffic flow prediction. IEEE Trans Intell Transp Syst 20(5):1847–1857. https://doi.org/10.1109/tits.2018.2843349

    Article  Google Scholar 

  2. Vlahogianni EI, Karlaftis MG, Golias JC (2014) Short-term traffic forecasting: where we are and where we’re going. Transp Res Pt C Emerg Technol 43:3–19. https://doi.org/10.1016/j.trc.2014.01.005

    Article  Google Scholar 

  3. Williams BM, Hoel LA (2003) Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J Transp Eng A Syst 129(6):664–672. https://doi.org/10.1061/(Asce)0733-947x(2003)129:6(664)

    Article  Google Scholar 

  4. Fusco G, Colombaroni C, Isaenko N (2016) Short-term speed predictions exploiting big data on large urban road networks. Transp Res Pt C Emerg Technol 73:183–201. https://doi.org/10.1016/j.trc.2016.10.019

    Article  Google Scholar 

  5. Ojeda LL, Kibangou AY, Wit CD (2013) Adaptive Kalman filtering for multi-step ahead traffic flow prediction. In: American Control Conference (ACC), pp 4724–4729

  6. Hu X, Liu T, Li Y, Cui Z (2021) An improved Euclidean distance weighted K-nearest neighbor model for traffic state forecasting. In: Transportation research board 100th annual meeting. Transportation Research Board, Washington DC, p 18

  7. Tang J, Chen X, Hu Z, Zong F, Han C, Li L (2019) Traffic flow prediction based on combination of support vector machine and data denoising schemes. Phys A. https://doi.org/10.1016/j.physa.2019.03.007

    Article  Google Scholar 

  8. Sun J, Sun J, Chen P (2014) Use of support vector machine models for real-time prediction of crash risk on urban expressways. Transport Res Rec 2432(1):91–98. https://doi.org/10.3141/2432-11

    Article  MathSciNet  Google Scholar 

  9. Wang J, Shi Q (2013) Short-term traffic speed forecasting hybrid model based on Chaos-wavelet analysis-support vector machine theory. Transp Res Pt C Emerg Technol 27:219–232. https://doi.org/10.1016/j.trc.2012.08.004

    Article  Google Scholar 

  10. Ren Q (2007) Research on time-space road network traffic congestion prediction and guide decision method. Southwest Jiaotong University

  11. Castillo E, Jiménez P, Menéndez JM, Nogal M (2012) A Bayesian method for estimating traffic flows based on plate scanning. Transportation 40(1):173–201. https://doi.org/10.1007/s11116-012-9443-4

    Article  Google Scholar 

  12. Yu B, Song X, Guan F, Yang Z, Yao B (2016) k-Nearest neighbor model for multiple-time-step prediction of short-term traffic condition. J Transp Eng A Syst 142(6):04016018. https://doi.org/10.1061/(asce)te.1943-5436.0000816

    Article  Google Scholar 

  13. Cai P, Wang Y, Lu G, Chen P, Ding C, Sun J (2016) A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting. Transp Res Pt C Emerg Technol 62:21–34. https://doi.org/10.1016/j.trc.2015.11.002

    Article  Google Scholar 

  14. Zheng Z, Su D (2014) Short-term traffic volume forecasting: a k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm. Transp Res Pt C Emerg Technol 43:143–157. https://doi.org/10.1016/j.trc.2014.02.009

    Article  MathSciNet  Google Scholar 

  15. Ma X, Zhuang D, He Z, Ma J, Wang Y (2017) Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors 17(4):818. https://doi.org/10.3390/s17040818

    Article  Google Scholar 

  16. Zheng F, Zuylen HV (2013) Urban link travel time estimation based on sparse probe vehicle data. Transp Res Pt C Emerg Technol 31:145–157. https://doi.org/10.1016/j.trc.2012.04.007

    Article  Google Scholar 

  17. Ye Q, Szeto WY, Wong SC (2012) Short-term traffic speed forecasting based on data recorded at irregular intervals. IEEE Trans Intell Transp Syst 13(4):1727–1737. https://doi.org/10.1109/Tits.2012.2203122

    Article  Google Scholar 

  18. Zheng H, Lin F, Feng X, Chen Y (2020) A hybrid deep learning model with attention-based Conv-LSTM networks for short-term traffic flow prediction. IEEE Trans Intell Transp Syst 22(11):6910–6920. https://doi.org/10.1109/TITS.2020.2997352

    Article  Google Scholar 

  19. Zhao L, Wang Q, Jin B, Ye C (2020) Short-term traffic flow intensity prediction based on CHS-LSTM. Arab J Sci Eng 45(12):10845–10857

    Article  Google Scholar 

  20. Zhao Z, Chen W, Wu X, Chen PC, Liu J (2017) LSTM network: a deep learning approach for short-term traffic forecast. IET Intell Transp Syst 11(2):68–75. https://doi.org/10.1049/iet-its.2016.0208

    Article  Google Scholar 

  21. 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. Transp Res Pt C Emerg Technol 54:187–197. https://doi.org/10.1016/j.trc.2015.03.014

    Article  Google Scholar 

  22. Yang HF, Dillon TS, Chen YP (2017) Optimized structure of the traffic flow forecasting model with a deep learning approach. IEEE Trans Neural Netw Learn Syst 28(10):2371–2381. https://doi.org/10.1109/TNNLS.2016.2574840

    Article  Google Scholar 

  23. Duan Y, Lv Y, Wang FY (2016) Performance evaluation of the deep learning approach for traffic flow prediction at different times. In: IEEE International Conference on Service Operations & Logistics, pp 223–227

  24. 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):2191–2201. https://doi.org/10.1109/TITS.2014.2311123

    Article  Google Scholar 

  25. Bustillos BI, Chiu Y-C (2011) Real-time freeway-experienced travel time prediction using N-curve and k nearest neighbor methods. Transport Res Rec J Transport Res Board 2243(1):127–137. https://doi.org/10.3141/2243-15

    Article  Google Scholar 

  26. Zhang N, Zhang Y, Lu H (2011) Seasonal autoregressive integrated moving average and support vector machine models. Transport Res Rec J Transport Res Board 2215(1):85–92. https://doi.org/10.3141/2215-09

    Article  Google Scholar 

  27. Yin X, Wu G, Wei J, Shen Y, Qi H, Yin B (2021) Deep learning on traffic prediction: methods, analysis and future directions. IEEE Trans Intell Transp Syst. https://doi.org/10.1109/tits.2021.3054840

    Article  Google Scholar 

  28. Khan Z, Khan SM, Dey K, Chowdhury M (2019) Development and evaluation of recurrent neural network-based models for hourly traffic volume and annual average daily traffic prediction. Transport Res Rec 2673(7):489–503. https://doi.org/10.1177/0361198119849059

    Article  Google Scholar 

  29. Lv YS, Duan YJ, Kang WW, Li ZX, Wang FY (2015) Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transp Syst 16(2):865–873. https://doi.org/10.1109/Tits.2014.2345663

    Article  Google Scholar 

  30. Ke R, Li W, Cui Z, Wang Y (2020) Two-stream multi-channel convolutional neural network for multi-lane traffic speed prediction considering traffic volume impact. Transport Res Rec 2674(4):459–470. https://doi.org/10.1177/0361198120911052

    Article  Google Scholar 

  31. Hosseini MK, Talebpour A (2019) Traffic prediction using time-space diagram: a convolutional neural network approach. Transport Res Rec 2673(7):425–435. https://doi.org/10.1177/0361198119841291

    Article  Google Scholar 

  32. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach

  33. Ji Z, Xiong KL, Pang YW, Li XL (2020) Video summarization with attention-based encoder-decoder networks. IEEE Trans Circuits Syst Video Technol 30(6):1709–1717. https://doi.org/10.1109/tcsvt.2019.2904996

    Article  Google Scholar 

  34. Wu P, Huang Z, Pian Y, Xu L, Li J, Chen K (2020) A combined deep learning method with attention-based LSTM model for short-term traffic speed forecasting. J Adv Transp. https://doi.org/10.1155/2020/8863724

    Article  Google Scholar 

  35. Yang F, Zhang H, Tao S (2021) Travel order quantity prediction via attention-based bidirectional LSTM networks. J Supercomput. https://doi.org/10.1007/s11227-021-04032-8

    Article  Google Scholar 

  36. Liu Q, Liu T, Cai Y, Xiong X, Hu Z (2021) Explanatory prediction of traffic congestion propagation mode: a self-attention based approach. Phys A 573:125940. https://doi.org/10.1016/j.physa.2021.125940

    Article  Google Scholar 

  37. Sun B, Sun T, Zhang Y, Jiao P (2020) Urban traffic flow online prediction based on multi-component attention mechanism. IET Intell Transport Syst 14(10):1249–1258. https://doi.org/10.1049/iet-its.2020.0004

    Article  Google Scholar 

  38. Shi XJ, Chen ZR, Wang H, Yeung DY, Wong WK, Woo WC (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in neural information processing systems, vol 28, La Jolla

  39. Du SD, Li TR, Gong X, Horng SJ (2020) A hybrid method for traffic flow forecasting using multimodal deep learning. Int J Comput Intell Syst 13(1):85–97. https://doi.org/10.2991/ijcis.d.200120.001

    Article  Google Scholar 

  40. Hou Y, Edara P (2018) Network scale travel time prediction using deep learning. Transport Res Rec 2672(45):115–123. https://doi.org/10.1177/0361198118776139

    Article  Google Scholar 

  41. Xiao Y, Yin H, Zhang Y, Qi H, Zhang Y, Liu Z (2021) A dual-stage attention-based Conv-LSTM network for spatio-temporal correlation and multivariate time series prediction. Int J Intell Syst 36(5):2036–2057. https://doi.org/10.1002/int.22370

    Article  Google Scholar 

  42. Shabarek A, Chien S, Hadri S (2020) Deep learning framework for freeway speed prediction in adverse weather. Transport Res Rec 2674(10):28–41. https://doi.org/10.1177/0361198120947421

    Article  Google Scholar 

  43. Bin Y, Shanhua W, Minghua W, Zhihong Z (2012) K-nearest neighbor short-term traffic flow prediction model. J Transp Eng 12(02):105–111

    Google Scholar 

  44. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. Computer Science

  45. Amap (2021) Obtain traffic situation data. https://lbs.amap.com/api/webservice/guide/api/trafficstatus/. Accessed 8 July 2021

  46. Kingma D, Ba J (2014) Adam: a method for stochastic optimization

  47. Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP (2003) Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci 43(6):1947–1958. https://doi.org/10.1021/ci034160g

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by Jiangsu Provincial Key Research and Development Program (No. BE20187544).

Author information

Authors and Affiliations

  1. Jiangsu Key Laboratory of Urban ITS, Southeast University, Southeast University Road #2, Nanjing, 211189, China

    Xiaojian Hu, Tong Liu, Xiatong Hao & Chenxi Lin

  2. Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing, China

    Xiaojian Hu

  3. National Demonstration Center for Experimental Road and Traffic Engineering Education (Southeast University), Nanjing, 211189, China

    Xiaojian Hu

  4. School of Transportation, Southeast University, Southeast University Road #2, Nanjing, 211189, China

    Xiaojian Hu

Authors
  1. Xiaojian Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiatong Hao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chenxi Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tong Liu.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, X., Liu, T., Hao, X. et al. Attention-based Conv-LSTM and Bi-LSTM networks for large-scale traffic speed prediction. J Supercomput 78, 12686–12709 (2022). https://doi.org/10.1007/s11227-022-04386-7

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-022-04386-7

Keywords

Search

Navigation