Abstract
Traffic flow prediction is a key component of intelligent transportation system, especially for increasingly complex urban traffic networks. An accurate flow prediction can help to relieve traffic congestion and reduce traffic accidents. However, the patterns of traffic flow are very complex and volatile, which will be affected by many factors, such as traffic accident, weather, point-of-interests, etc. It is still a challenging issue due to the high nonlinearity and dynamicity of traffic flow. In this paper, we propose a multi-attention predictive recurrent neural networks (MAPredRNN) for traffic flow prediction by dynamic spatio-temporal data fusion. First, convolutional neural network and predictive recurrent neural network are used to obtain the spatio-temporal information of the closeness, periodicity and trend features. And then, multi-attention mechanism is employed to further extract feature fusing information of closeness, periodicity and trend. Experimental results conducted on two real datasets show that our proposed method outperforms the compared algorithms.
Similar content being viewed by others
References
Chen Y, Lv Y, Ye P, Zhu F (2020) Traffic-Condition-Awareness Ensemble learning for traffic flow prediction. IFAC-PapersOnLine 53(5):582–587
Do LN, Vu HL, Vo BQ, Liu Z, Phung D (2019) An effective spatial-temporal attention based neural network for traffic flow prediction. Transp Res C Emerg Technol 108:12–28
Feng X, Ling X, Zheng H, Chen Z, Xu Y (2019) Adaptive multi-kernel svm with spatial–temporal correlation for short-term traffic flow prediction. IEEE Trans Intell Transp Syst 20(6):2001–2013
Guancen Lin Aijing Lin DG (2022) Using support vector regression and k-nearest neighbors for short-term traffic flow prediction based on maximal information coefficient. Inf Sci 608:517–531
Guo S, Lin Y, Feng N, Song C, Wan H (2019) Attention based Spatial-Temporal graph convolutional networks for traffic flow forecasting. In: Proceedings of the 33th AAAI conference on artificial intelligence, vol. 33, pp 922–929
Guo S, Lin Y, Li S, Chen Z, Wan H (2019) Deep Spatial–Temporal 3D convolutional neural networks for traffic data forecasting. IEEE Trans Intell Transp Syst 20(10):3913–3926
Huang X, Tang J, Yang X, Xiong L (2022) A time-dependent attention convolutional LSTM method for traffic flow prediction. Appl Intell 52:17371–17386
Klepsch J, Klüppelberg C, Wei T (2017) Prediction of functional ARMA processes with an application to traffic data. Econometrics and Statistics 1:128–149
Kumar SV (2017) Traffic flow prediction using Kalman filtering technique. Procedia Eng 187:582–587
Lin Z, Feng J, Lu Z, Li Y, Jin D (2019) DeepSTN+: context-aware spatial-temporal neural network for crowd flow prediction in Metropolis. In: Proceedings of the 33th AAAI conference on artificial intelligence, vol. 33, pp 1020–1027
Liu J, Wei G (2004) A summary of traffic flow forecasting methods. J Highw Transp Res Dev 21:82–85
Lv M, Hong Z, Chen L, Chen T, Zhu T, Ji S (2020) Temporal multi-graph convolutional network for traffic flow prediction. IEEE Trans Intell Transp Syst 22(6):3337–3348
Lv M, Hong Z, Chen L, Chen T, Zhu T, Ji S (2021) Temporal Multi-Graph convolutional network for traffic flow prediction. IEEE Trans Intell Transp Syst 22(6):3337–3348
Qi T, Li G, Chen L, Xue Y (2022) ADGCN: an asynchronous dilation graph convolutional network for traffic flow prediction. IEEE Internet Things J 9(5):4001–4014
Ren Y, Zhao D, Luo D, Ma H, Duan P (2020) Global-Local Temporal convolutional network for traffic flow prediction. IEEE Trans Intell Transp Syst 23(2):1578–1584
Shen XJ, Zhang JT, Han DJ (2018) Short-term traffic flow prediction model based on gradient boosting regression tree. Comput Sci 45(6):222–227
Shi X, Chen Z, Wang H, Yeung DY, Wong WK, Woo Wc (2015) Convolutional LSTM Network: A machine learning approach for precipitation nowcasting. Adv Neural Inf Process Syst 28:802–810
Wang S, Miao H, Li J, Cao J (2021) Spatio-Temporal Knowledge transfer for urban crowd flow prediction via deep attentive adaptation networks. IEEE Trans Intell Transp Syst 23(5):4695–4705
Wang Y, Long M, Wang J, Gao Z, Yu PS (2017) PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs. Adv Neural Inf Process Syst 30:879–888
Yang L (2020) Uncertainty prediction method for traffic flow based on K-nearest neighbor algorithm. J Intell Fuzzy Syst 39(2):1489–1499
Yu K, Qin X, Jia Z, Du Y, Lin M (2021) Cross-attention fusion based spatial-temporal multi-graph convolutional network for traffic flow prediction. Sensors 21(24):8468
Zhang J, Zheng Y, Qi D (2017) Deep Spatio-Temporal residual networks for citywide crowd flows prediction. In: Proceedings of the 31th AAAI conference on artificial intelligence, pp 1–7
Zhang X, Huang C, Xu Y, Xia L, Dai P, Bo L, Zhang J, Zheng Y (2021) Traffic flow forecasting with Spatial-Temporal graph diffusion network. In: Proceedings of the 35th AAAI conference on artificial intelligence, vol. 35, pp 15008–15015
Zhao L, Song Y, Zhang C, Liu Y, Wang P, Lin T, Deng M, Li H (2020) T-gcn: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst 21(9):3848–3858
Zheng Z, Shi L, Sun L, Du J (2020) Short-Term traffic flow prediction based on sparse regression and Spatio-Temporal data fusion. IEEE Access 8:142111–142119
Zonoozi A, Kim Jj, Li XL, Cong G (2018) Periodic-CRN: a convolutional recurrent model for crowd density prediction with recurring periodic patterns. In: Proceedings of the 27th international joint conferences on artificial intelligence, pp 3732–3738
Acknowledgements
This research was funded by the National Natural Science Foundation of China under Grant No.62062033 and No.62067002, and the Natural Science Foundation of Jiangxi Province under Grant No.20212BAB202008.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Huang, X., Jiang, Y. & Tang, J. MAPredRNN: multi-attention predictive RNN for traffic flow prediction by dynamic spatio-temporal data fusion. Appl Intell 53, 19372–19383 (2023). https://doi.org/10.1007/s10489-023-04494-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04494-8