Robust Deep Learning Architecture for Traffic Flow Estimation from a Subset of Link Sensors
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 146, Issue 1
Abstract
Traffic flow data are needed for traffic management and control applications as well as for transportation planning issues. Such data are usually collected from traffic sensors; however, it is not practical or even feasible to deploy traffic sensors on all of a network’s links. Instead, it is necessary to extend the information acquired from a subset of link flows to estimate the entire network’s traffic flow. To this end, this study proposes a robust deep learning architecture based on a stacked sparse autoencoders (SAEs) model for a precise estimation of the whole network’s traffic flow with an already-deployed sensor set. The proposed deep learning architecture has two consequent components: a deep learning model based on the SAEs and a fully connected layer. First, the SAEs model is used to extract traffic flow features and reach a meaningful pattern of the relation between the traffic flow data and network structure. Subsequently, the fully connected layer is used for the traffic flow estimation. Then, the whole architecture is fine-tuned to update its parameters in order to enhance the traffic flow estimation. For training the proposed deep learning architecture, synthetic link flow data are randomly generated from the network’s prior demand information. The performance of the proposed model is evaluated then validated using two real networks. A third medium real-size network is used to measure the robustness of applying the proposed methodology to this specific problem of traffic flow estimation.
Get full access to this article
View all available purchase options and get full access to this article.
References
Arevalo, J., F. A. González, R. Ramos-Pollán, J. L. Oliveira, and M. A. G. Lopez. 2016. “Representation learning for mammography mass lesion classification with convolutional neural networks.” Comput. Methods Programs Biomed. 127 (Apr): 248–257. https://doi.org/10.1016/j.cmpb.2015.12.014.
Asencio-Cortés, G., E. Florido, A. Troncoso, and F. Martínez-Álvarez. 2016. “A novel methodology to predict urban traffic congestion with ensemble learning.” Soft Comput. 20 (11): 4205–4216. https://doi.org/10.1007/s00500-016-2288-6.
Bengio, Y., A. Courville, and P. Vincent. 2013. “Representation learning: A review and new perspectives.” IEEE Trans. Pattern Anal. Mach. Intell. 35 (8): 1798–1828. https://doi.org/10.1109/TPAMI.2013.50.
Bengio, Y., P. Lamblin, D. Popovici, and H. Larochelle. 2007. “Greedy layer-wise training of deep networks.” In Vol. 19 of Proc., Advances in Neural Information Processing Systems. Vancouver, BC: Neural Information Processing Systems Foundation.
Bianco, L., G. Confessore, and M. Gentili. 2006. “Combinatorial aspects of the sensor location problem.” Ann. Oper. Res. 144 (1): 201–234. https://doi.org/10.1007/s10479-006-0016-9.
Bianco, L., G. Confessore, and P. Reverberi. 2001. “A network based model for traffic sensor location with implications on O/D matrix estimates.” Transp. Sci. 35 (1): 50–60. https://doi.org/10.1287/trsc.35.1.50.10140.
Bonsall, P., P. Firmin, M. Anderson, I. Palmer, and P. Balmforth. 1997. “Validating the results of a route choice simulator.” Transp. Res. Part C: Emerging Technol. 5 (6): 371–387. https://doi.org/10.1016/S0968-090X(98)00003-5.
Castillo, E., A. J. Conejo, J. M. Menéndez, and P. Jiménez. 2008a. “The observability problem in traffic network models.” Comput.-Aided Civ. Infrastruct. Eng. 23 (3): 208–222. https://doi.org/10.1111/j.1467-8667.2008.00531.x.
Castillo, E., P. Jimenez, J. M. Menendez, and A. J. Conejo. 2008b. “The observability problem in traffic models: Algebraic and topological methods.” IEEE Trans. Intell. Transp. Syst. 9 (2): 275–287. https://doi.org/10.1109/TITS.2008.922929.
Castillo, E., J. M. Menéndez, and P. Jiménez. 2008c. “Trip matrix and path flow reconstruction and estimation based on plate scanning and link observations.” Transp. Res. Part B: Methodol. 42 (5): 455–481. https://doi.org/10.1016/j.trb.2007.09.004.
Castillo, E., J. M. Menéndez, and S. Sánchez-Cambronero. 2008d. “Predicting traffic flow using Bayesian networks.” Transp. Res. Part B: Methodol. 42 (5): 482–509. https://doi.org/10.1016/j.trb.2007.10.003.
Castillo, E., J. M. Menéndez, and S. Sánchez-Cambronero. 2008e. “Traffic estimation and optimal counting location without path enumeration using Bayesian networks.” Comput.-Aided Civ. Infrastruct. Eng. 23 (3): 189–207. https://doi.org/10.1111/j.1467-8667.2008.00526.x.
Castillo, E., M. Nogal, A. Rivas, and S. Sánchez-Cambronero. 2013. “Observability of traffic networks. Optimal location of counting and scanning devices.” Transportmetrica B: Transp. Dyn. 1 (1): 68–102. https://doi.org/10.1080/21680566.2013.780987.
Chen, A., P. Chootinan, and W. W. Recker. 2005. “Examining the quality of synthetic origin—Destination trip table estimated by path flow estimator.” J. Transp. Eng. 131 (7): 506–513. https://doi.org/10.1061/(ASCE)0733-947X(2005)131:7(506).
Chen, X.-W., and X. Lin. 2014. “Big data deep learning: Challenges and perspectives.” IEEE Access 2 (May): 514–525. https://doi.org/10.1109/ACCESS.2014.2325029.
Chin, F., M. Chrobak, and L. Yan. 2009. “Algorithms for placing monitors in a flow network.” In Algorithmic aspects in information and management. Berlin: Springer.
Chootinan, P., A. Chen, and H. Yang. 2005. “A bi-objective traffic counting location problem for origin-destination trip table estimation.” Transportmetrica 1 (1): 65–80. https://doi.org/10.1080/18128600508685639.
Daganzo, C. F., and Y. Sheffi. 1977. “On stochastic models of traffic assignment.” Transp. Sci. 11 (3): 253–274. https://doi.org/10.1287/trsc.11.3.253.
Dimitrakopoulos, G., and P. Demestichas. 2010. “Intelligent transportation systems.” IEEE Veh. Technol. Mag. 5 (1): 77–84. https://doi.org/10.1109/MVT.2009.935537.
Duan, Y., Y. Lv, Y.-L. Liu, and F.-Y. Wang. 2016. “An efficient realization of deep learning for traffic data imputation.” Transp. Res. Part C: Emerging Technol. 72 (Nov): 168–181. https://doi.org/10.1016/j.trc.2016.09.015.
Fu, C., N. Zhu, S. Ling, S. Ma, and Y. Huang. 2016. “Heterogeneous sensor location model for path reconstruction.” Transp. Res. Part B: Methodol. 91 (Sep): 77–97. https://doi.org/10.1016/j.trb.2016.04.013.
Gan, L., H. Yang, and S. C. Wong. 2005. “Traffic counting location and error bound in origin-destination matrix estimation problems.” J. Transp. Eng. 131 (7): 524–534. https://doi.org/10.1061/(ASCE)0733-947X(2005)131:7(524).
Gang, X., W. Kang, F. Wang, F. Zhu, Y. Lv, X. Dong, J. Riekki, and S. Pirttikangas. 2015. “Continuous travel time prediction for transit signal priority based on a deep network.” In Proc., 2015 IEEE 18th Int. Conf. on Intelligent Transportation Systems. New York: IEEE.
Gentili, M., and P. Mirchandani. 2011. “Survey of models to locate sensors to estimate traffic flows.” Transp. Res. Rec. 2243 (1): 108–116. https://doi.org/10.3141/2243-13.
Gentili, M., and P. B. Mirchandani. 2005. “Locating active sensors on traffic networks.” Ann. Oper. Res. 136 (1): 229–257. https://doi.org/10.1007/s10479-005-2047-z.
Gentili, M., and P. B. Mirchandani. 2012. “Locating sensors on traffic networks: Models, challenges and research opportunities.” Transp. Res. Part C: Emerging Technol. 24 (Oct): 227–255. https://doi.org/10.1016/j.trc.2012.01.004.
Gravelines, C. 1991. Deep learning via stacked sparse autoencoders for automated voxel-wise brain parcellation based on functional connectivity. London: Univ. of Western Ontario.
Hadavi, M., and Y. Shafahi. 2016. “Vehicle identification sensor models for origin–destination estimation.” Transp. Res. Part B: Methodol. 89 (Jul): 82–106. https://doi.org/10.1016/j.trb.2016.03.011.
Hazelton, M. L. 2000. “Estimation of origin–destination matrices from link flows on uncongested networks.” Transp. Res. Part B: Methodol. 34 (7): 549–566. https://doi.org/10.1016/S0191-2615(99)00037-5.
He, S.-X. 2013. “A graphical approach to identify sensor locations for link flow inference.” Transp. Res. Part B: Methodol. 51 (May): 65–76. https://doi.org/10.1016/j.trb.2013.02.006.
Hinton, G. E., S. Osindero, and Y.-W. Teh. 2006. “A fast learning algorithm for deep belief nets.” Neural Comput. 18 (7): 1527–1554. https://doi.org/10.1162/neco.2006.18.7.1527.
Hosseini-Asl, E., J. M. Zurada, and O. Nasraoui. 2016. “Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints.” IEEE Trans. Neural Networks Learn. Syst. 27 (12): 2486–2498. https://doi.org/10.1109/TNNLS.2015.2479223.
Hu, S.-R., S. Peeta, and C.-H. Chu. 2009. “Identification of vehicle sensor locations for link-based network traffic applications.” Transp. Res. Part B: Methodol. 43 (8): 873–894. https://doi.org/10.1016/j.trb.2009.02.008.
Hu, S.-R., S. Peeta, and H.-T. Liou. 2016. “Integrated determination of network origin–destination trip matrix and heterogeneous sensor selection and location strategy.” IEEE Trans. Intell. Transp. Syst. 17 (1): 195–205. https://doi.org/10.1109/TITS.2015.2473691.
Huang, W., G. Song, H. Hong, and K. Xie. 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.
Jia, Y., J. Wu, and Y. Du. 2016. “Traffic speed prediction using deep learning method.” In Proc., 2016 IEEE 19th Int. Conf. on Intelligent Transportation Systems. New York: IEEE.
Larochelle, H., Y. Bengio, J. Louradour, and P. Lamblin. 2009. “Exploring strategies for training deep neural networks.” J. Mach. Learn. Res. 10 (Jan): 1–40.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Lee, H., C. Ekanadham, and A. Y. Ng. 2008. Sparse deep belief net model for visual area V2: Advances in neural information processing systems. Vancouver, BC: Neural Information Processing Systems Foundation.
Lemieux, J., and Y. Ma. 2015. “Vehicle speed prediction using deep learning.” In Proc., Vehicle Power and Propulsion Conf. New York: IEEE.
Liu, Y., N. Zhu, S. Ma, and N. Jia. 2015. “Traffic sensor location approach for flow inference.” IET Intel. Transport Syst. 9 (2): 184–192. https://doi.org/10.1049/iet-its.2014.0023.
Lv, Y., Y. Duan, W. Kang, Z. Li, and F.-Y. Wang. 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.
Maher, M. 1998. “Algorithms for logit-based stochastic user equilibrium assignment.” Transp. Res. Part B: Methodol. 32 (8): 539–549. https://doi.org/10.1016/S0191-2615(98)00015-0.
Marc’Aurelio Ranzato, C. P., S. Chopra, and Y. L. Cun. 2007. “Efficient learning of sparse representations with an energy-based model.” In Proc., Advances in Neural Information Processing Systems. Vancouver, BC: Neural Information Processing Systems Foundation.
Mínguez, R., S. Sánchez-Cambronero, E. Castillo, and P. Jiménez. 2010. “Optimal traffic plate scanning location for OD trip matrix and route estimation in road networks.” Transp. Res. Part B: Methodol. 44 (2): 282–298. https://doi.org/10.1016/j.trb.2009.07.008.
Ng, M. 2012. “Synergistic sensor location for link flow inference without path enumeration: A node-based approach.” Transp. Res. Part B: Methodol. 46 (6): 781–788. https://doi.org/10.1016/j.trb.2012.02.001.
Ng, M. 2013. “Partial link flow observability in the presence of initial sensors: Solution without path enumeration.” Transp. Res. Part E: Logist. Transp. Rev. 51 (May): 62–66. https://doi.org/10.1016/j.tre.2012.12.002.
Oliveira, T. P., J. S. Barbar, and A. S. Soares. 2016. “Computer network traffic prediction: A comparison between traditional and deep learning neural networks.” Int. J. Big Data Intell. 3 (1): 28–37. https://doi.org/10.1504/IJBDI.2016.073903.
Owais, M., G. S. Moussa, and K. F. Hussain. 2019. “Sensor location model for O/D estimation: Multi-criteria meta-heuristics approach.” Oper. Res. Perspect. 6: 100100. https://doi.org/10.1016/j.orp.2019.100100.
Owais, M., M. K. Osman, and G. Moussa. 2016. “Multi-objective transit route network design as set covering problem.” IEEE Trans. Intell. Transp. Syst. 17 (3): 670–679. https://doi.org/10.1109/TITS.2015.2480885.
Palm, R. B. 2012. Prediction as a candidate for learning deep hierarchical models of data. Lyngby, Denmark: Technical Univ. of Denmark.
Pérez-Cruz, F. 2008. “Kullback-Leibler divergence estimation of continuous distributions.” In Proc., IEEE Int. Symp. on Information Theory. New York: IEEE.
Powell, W. B., and Y. Sheffi. 1982. “The convergence of equilibrium algorithms with predetermined step sizes.” Transp. Sci. 16 (1): 45–55. https://doi.org/10.1287/trsc.16.1.45.
Prashker, J. N., and S. Bekhor. 2004. “Route choice models used in the stochastic user equilibrium problem: A review.” Transp. Rev. 24 (4): 437–463. https://doi.org/10.1080/0144164042000181707.
Schmidhuber, J. 2015. “Deep learning in neural networks: An overview.” Neural Netw. 61 (Jan): 85–117. https://doi.org/10.1016/j.neunet.2014.09.003.
Sheffi, Y. 1985. Urban transportation network. Englewoods Cliffs, NJ: Prentice Hall.
Spiess, H. 1990. “Conical volume-delay functions.” Transp. Sci. 24 (2): 153–158. https://doi.org/10.1287/trsc.24.2.153.
Vincent, P., H. Larochelle, Y. Bengio, and P.-A. Manzagol. 2008. “Extracting and composing robust features with denoising autoencoders.” In Proc., 25th Int. Conf. on Machine Learning. New York: Association for Computing Machinery.
Vincent, P., H. Larochelle, I. Lajoie, Y. Bengio, and P.-A. Manzagol. 2010. “Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion.” J. Mach. Learn. Res. 11 (Dec): 3371–3408.
Wang, N., M. Gentili, and P. Mirchandani. 2012. “Model to locate sensors for estimation of static origin-destination volumes given prior flow information.” Transp. Res. Rec. 2283 (1), 67–73.
Xu, X., H. K. Lo, A. Chen, and E. Castillo. 2016. “Robust network sensor location for complete link flow observability under uncertainty.” Transp. Res. Part B: Methodol. 88 (Jun): 1–20. https://doi.org/10.1016/j.trb.2016.03.006.
Yang, C., P. Chootinan, and A. Chen. 2003. “Traffic counting location planning using genetic algorithm.” J. Eastern Asia Soc. Transp. Stud. 5 (Jan): 898–913.
Yang, H., L. Gan, and W. Tang. 2001. “Determining cordons and screen lines for origin-destination trip studies.” In Vol. 3 of Proc., Eastern Asia Society for Transportation Studies. Tokyo: Eastern Asia Society for Transportation Studies.
Yang, H., Y. Iida, and T. Sasaki. 1991. “An analysis of the reliability of an origin-destination trip matrix estimated from traffic counts.” Transp. Res. Part B: Methodol. 25 (5): 351–363. https://doi.org/10.1016/0191-2615(91)90028-H.
Yang, H., and J. Zhou. 1998. “Optimal traffic counting locations for origin–destination matrix estimation.” Transp. Res. Part B: Methodol. 32 (2): 109–126. https://doi.org/10.1016/S0191-2615(97)00016-7.
Yim, P. K., and W. H. Lam. 1998. “Evaluation of count location selection methods for estimation of OD matrices.” J. Transp. Eng. 124 (4): 376–383. https://doi.org/10.1061/(ASCE)0733-947X(1998)124:4(376).
Zangui, M., Y. Yin, and S. Lawphongpanich. 2015. “Sensor location problems in path-differentiated congestion pricing.” Transp. Res. Part C: Emerging Technol. 55 (Jun): 217–230. https://doi.org/10.1016/j.trc.2015.01.012.
Zhou, X., and G. F. List. 2010. “An information-theoretic sensor location model for traffic origin-destination demand estimation applications.” Transp. Sci. 44 (2): 254–273. https://doi.org/10.1287/trsc.1100.0319.
Zhou, X., and H. S. Mahmassani. 2006. “Dynamic origin-destination demand estimation using automatic vehicle identification data.” IEEE Trans. Intell. Transp. Syst. 7 (1): 105–114. https://doi.org/10.1109/TITS.2006.869629.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 146 • Issue 1 • January 2020
Copyright
©2019 American Society of Civil Engineers.
History
Received: Dec 4, 2018
Accepted: May 31, 2019
Published online: Oct 22, 2019
Published in print: Jan 1, 2020
Discussion open until: Mar 22, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.