Travel Time Prediction of Urban Road Based on Deep Learning

doi:10.16182/j.issn1004731x.joss.201710011

Abstract

Abstract: Travel time prediction of urban road is a significant support for urban intelligent transportation system. Four types of LSTM neural network architecture were selected to predict the urban road travel time. The number of nodes in the LSTM hidden layer was fixed to determine the optimal input length of the model. The input length of the model was fixed and the predictive performance of the four LSTM models under different hidden layer nodes and considering spatial correlation were tested respectively. The performance of spatial LSTM model was compared with four traditional models, for example, BP neural network. The results show that the LSTM model with spatial correlation has better fitting and training ability than the four traditional models.

Key words: traffic engineering, LSTM, travel time prediction, spatial correlation, deep learning

CLC Number:

TP391

Zhang Weiwei, Li Ruimin, Xie Zhongjiao. Travel Time Prediction of Urban Road Based on Deep Learning[J]. Journal of System Simulation, 2017, 29(10): 2309-2316.

References

[1] Lipton Z C, Berkowitz J, Elkan C. A Critical Review of Recurrent Neural Networks for Sequence Learning [J/OL]. (2015-10-17) [2017-01-10]. https://arxiv.org/ abs/1506.00019.
[2] Lecun Y, Bengio Y, Hinton G.Deep learning[J]. Nature (S0028-0836), 2015, 521: 436-444.
[3] Silver D, Huang A, Maddison C J, et al.Mastering the game of Go with deep neural networks and tree search[J]. Nature(S0028-0836), 2016, 529(7587): 484-489.
[4] Wang F, Zhang J J, Zheng X, et al.Where Does AlphaGo Go: From Church-Turing Thesis to AlphaGo Thesis and Beyond[J]. IEEE/CAA Journal of Automatica Sinica (S2329-9266), 2016, 3(2): 113-120.
[5] Zhang J, Chen H, Zhou H, et al.Freeway Travel Time Prediction Research Based on A Deep Learning Approach [C]// 4th International Conference on Advanced Materials and Information Technology Processing (AMITP 2016), Guilin, China, Atlantis: Atlantis Press, 2016: 487-493.
[6] Lv Y, Duan Y, Kang W, et al.Traffic Flow Prediction With Big Data: A Deep Learning Approach[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2015, 16(2): 1-9.
[7] Duan Y, Lv Y, Liu Y, et al.An efficient realization of deep learning for traffic data imputation[J]. Transportation Research Part C: Emerging Technologies(S0968-090X), 2016, 72: 168-181.
[8] Siripanpornchana C, Panichpapiboon S, Chaovalit P.Travel-time prediction with deep learning[C]// 2016 IEEE Region 10 Conference (TENCON). USA: IEEE, 2016.
[9] Wang J, Gu Q, Wu J.Traffic Speed Prediction and Congestion Source Exploration: A Deep Learining Method[C]// 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, Spain, 2016. USA: IEEE, 2016.
[10] Duan Y, Lv Y, Wang F.Travel time prediction with LSTM neural network[C]// 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 2016. USA: IEEE, 2016.
[11] Ma X, Tao Z, Wang Y, et al.Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C: Emerging Technologies(S0968-090X), 2015, 54: 187-197.
[12] Chreiter S H, Schmidhuber J.Long short-term memory[J]. Neural Computation(S1047-3211), 1997, 9(8): 1735-1780.
[13] Gers F E A, Schmidhuber J, Cummins F R. Learning to forget: continual prediction with LSTM[J]. Neural Computation(S 0899-7667), 2000, 12(10): 2451-2471.
[14] Gers F A, Schmidhuber J.Recurrent nets that time and count[C]// Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy, 2000. USA: IEEE, 2000.
[15] Gers F A, Schmidhuber E.LSTM recurrent networks learn simple context-free and context-sensitive languages[J]. IEEE Transactions on Neural Networks (S1045-9227), 2001, 12(6): 1333-1340.