Abstract
To solve the problem of fuzziness and uncertainty of traffic states in signalized intersection, a method was proposed for estimating traffic condition based on stacked de-noising auto-encoder model. The simulation data and empirical data were used to train the model, and the K-means clustering method was used to determine the traffic state thresholds and the data were divided into three categories based on the threshold values. Relevant features based on the reconstruction theory of de-noising auto-encoder were automatically extracted, and unsupervised greedy layer-wise pre-training and supervised fine-tuning were utilized to train the deep auto-encoder network, so that it had good robust performance on obtaining the traffic state characters with low quality in the complex environment. From the experimental results, the proposed method obtains an accuracy of 91.5% in simulation data and 88% in empirical data, which is better by 7.1% than using decision tree model.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Wu, X., & Liu, H. X. (2011). A shockwave profile model for traffic flow on congested urban arterials. Transportation Research Part B, 45(10), 1768–1786.
Tang, K. S., Mei, Y., & Li, K. P. (2014). A simulation-based evaluation of traffic state estimation accuracy by using floating car data in complex road networks. Journal of Tongji University: Natural Science, 09, 1347–1351.
Levin, M., & Krause, G. M. (1978). Incident detection: A Bayesian approach (pp. 52–58). Washington, D.C.: Transportation Research Record.
Xu, T., Yang, X. G., Xu, A. G., & Zhang, M. (2011). Urban road traffic state estimation based on data fusion. Computer Engineering and Applications, 47(07), 218–221.
Zhao, F. B., & Sun, M. (2006). A method of traffic state estimation based on fuzzy cluster. Microcomputer Application, 22(02), 9–11.
Dong, C. J., Shao, C. F., Zhuge, C. X., & Li, H. X. (2013). Estimating traffic flow models for urban expressway based on measurement data. Journal of Transportation Systems Engineering and Information Technology, 13(3), 46–59.
Zhang, L., Yang, W., & Liu, T. (2014). A Naive Bayesian classifier-based algorithm for freeway traffic incident detection. Journal of Tongji University: Natural Science, 42(4), 558–563.
Huang, W., Hong, H., Li, M., Hu, W., Song, G., & Xie, K. (2013). Deep architecture for traffic flow prediction advanced data mining and applications (pp. 165–176). Berlin: Springer.
Ma, X., Yu, H., Wang, Y., & Wang, Y. (2014). Large-scale transportation network congestion evolution prediction using deep learning theory. PLoS ONE, 10(3), e0119044.
Niu, X., Zhu, Y., Cao, Q., Zhao, L., & Xie, W. (2015). A novel urban traffic prediction mechanism for smart city using learning approach. In L. Sun, H. Ma, D. Fang, J. Niu & W. Wang (Eds.), Advances in wireless sensor networks (Vol. 501, pp. 548–557). Berlin: Springer.
Hong, H., Huang, W., Song, G., & Xie, K. (2014). Metric-based multi-task grouping neural network for traffic flow forecasting. In Advances in neural networks—ISNN 2014 (pp. 499–507).
Tan, J., & Wang, S. (2015). Research on prediction model for traffic congestion based on deep learning. Application Research of Computers, 32(10), 2951–2954.
Yin, S. L., & Zhao, Y. N. (2015). Practice and research on deep learning applied in urban traffic flow prediction. Modern Electronics Technique, 38(15), 158–162.
Hinton, G. E., & Salakhutdinov, R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504–507.
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P. A. (2010). Stacked de-noising auto-encoders: Learning useful representations in a deep network with a local de-noising criterion. Journal of Machine Learning Research, 11(6), 3371–3408.
Breiman, L., & Friedman, J. H. (1984). Classification and regression trees (wadsworth statistics/probability). Biometrics, 40(3), 358.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xiang, J., Chen, Z. Traffic State Estimation of Signalized Intersections Based on Stacked Denoising Auto-Encoder Model. Wireless Pers Commun 103, 625–638 (2018). https://doi.org/10.1007/s11277-018-5466-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-018-5466-2