Sage Journals: Discover world-class research

Abstract

The traffic index prediction plays an important role in many intelligent transportation applications. The challenge mainly comes from the strong nonlinearities in the changing of traffic index, which is caused by transitions of various traffic states including smooth traffic, congestion, breakdown and recovery. Deep learning performs well in capturing and describing the nonlinear relationship among variables. This paper uses a Sequence to Sequence (Seq2Seq) deep learning framework to predict the traffic index. In the proposed method, we use Long Short Term Memory (LSTM) as the basic circulating unit. And the LSTM units are stacked to extract the time changing characteristic and the periodic characteristic of the input traffic index sequence. Besides, the extracted feature vectors are decoded by another single layer LSTM to predict the traffic index of each time after inputting sequence. Experiments are conducted on Beijing traffic index datasets. The proposed method outperformed Autoregressive Integrated Moving Average Model (ARIMA) and LSTM under some commonly used evaluation metrics.

Keywords

Urban traffic traffic index prediction sequence to sequence learning

Get full access to this article

View all access options for this article.

References

D.W.

Wang

Y.D.

and Jia

L.M.

, Real-time road traffic state prediction based on ARIMA and Kalman filter, Frontiers of Information Technology & Electornic Engineering 18(2) (2017), 287–303.

and Zhang

, Research on short-term traffic flow prediction based on wavelet de-noising preprocessing, in: International Conference on Natural Computation, 2013, pp. 252–256.

Wang

and Zhang

B.W.

, Short-term traffic flow prediction based on Wavelet Analysis and Hidden Markov Model, Energy Conservation & Environmental Protection in Transportation 18(1) (2018), 81–88.

Castro-Neto

Jeong

Y.S.

and Jeong

M.K.

, Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions, Expert Systems with Applications 36(3-part-P2) (2019), 6164–6173.

Hochreiter

and Schmidhuber

, Long Short-Term Memory, Neural computation, 9(8) (1997), 1735–1780.

Kang

and Chen

, Short-term traffic flow prediction with LSTM recurrent neural network, in: International Conference on Intelligent Transportation Systems, 2017, pp. 1–6.

Zhu

J.Z.

Cao

J.X.

and Zhu

, Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections, Transportation Research 47 (2014), 139–154.

Chen

and Li

, A novel fuzzy deep-learning approach to traffic flow prediction with uncertain spatial-temporal data features, in: Future Generation Computer Systems, 2018, pp. 78–88.

Zheng

Lee

and Shi

, Short-term freeway traffic flow prediction: Bayesian combined neural network approach, Journal of Transportation Engineering 132(2) (2006), 114–121.

10.

Bian

and Qiu

, The prediction of foundation pit based on genetic back propagation neural network, Journal of Computational Methods in Sciences and Engineering 19(3) (2019), 707–717.

11.

Wang

X.X.

and Xun

L.H.

, Study on short-time traffic flow prediction based on deep learning, Journal of Transportation Systems Engineering and Information Technology 18(1) (2018), 81–88.

12.

Tan

and Wang

S.C.

, Research on traffic congestion prediction model based on deep learning, Application Research of Computers 32(10) (2015), 2951–2954.

13.

Liu

M.Y.

J.P.

and Wang

Y.B.

, Traffic flow prediction based on deep learning, Journal of System Simulation 30(11) (2018), 77–82.

14.

Cho

Van Merriënboer

and Gulcehre

, Learning phrase representations using RNN encoder-decoder for statistical machine translation, Empirical Methods in Natural Language Processing, 2014, 1724–1734.

15.

Venugopalan

Rohrbach

and Donahue

, Sequence to sequence – video to text, in: International Conference on Computer Vision, 2015, pp. 4534–4542.

16.

Sutskever

Vinyals

and Le

Q.V.

, Sequence to Sequence Learning with Neural Networks, in: Neural Information Processing Systems, 2014, pp. 3104–3112.

17.

Zhu

and Zhang

, Generating research of image caption based on improved NIC algorithm, Journal of Computational Methods in Sciences and Engineering 19(2) (2019), 353–366.

18.

Kingma

D.P.

and Ba

, Adam: A method for stochastic optimization, Computer Science, 2014, 1–5.

19.

Wang

, Traffic flow prediction based on recurrent neural network, Ph.D. Dissertation, Yunnan University, 2017.

Traffic index prediction based on sequence to sequence learning

Abstract

Keywords

Get full access to this article

References