Self-Supervised Deep Learning Framework for Anomaly Detection in Traffic Data
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 148, Issue 5
Abstract
The current state of practice in traffic data quality control features rule-based data checking and validation processes, where the rules are subjective and insensitive to variation inherited with traffic data. In this paper, self-supervised deep learning approaches were explored to leverage the existence of multiple sources of traffic volume data, which permitted cross-checking of one data source against another for improved robustness. Two types of models were developed, aiming at detecting data anomalies at two distinct timescales. Particularly, a novel variational autoencoder (VAE)-based model was formulated for discerning data anomalies at the daily level and four recurrent model structures, including recurrent neural networks (RNN), gated recurrent units (GRU), long short-term memory (LSTM) units, and liquid time constant (LTC) networks, were evaluated for detecting anomalies in finer incremental timescales (i.e., 5-min intervals). The effectiveness of the proposed methods was demonstrated using two independent sources of traffic data from the Georgia Department of Transportation: (1) traffic counts collected by inductive loops as part of the statewide traffic count program, and (2) traffic volumes acquired by a video detection system as part of the Georgia 511, an advanced traveler information system in Georgia. Based on our experiments, the VAE-based model achieved a precision of 0.95, recall of 0.92, and score of 0.94. Among the recurrent models, the fully connected LTC produced the lowest prediction error and achieved a precision of 0.82, recall of 0.88, and score of 0.85.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The work presented in this paper is part of a research project (RP 20-07) sponsored by the Georgia Department of Transportation. The contents of this paper reflect the views of the authors, who are solely responsible for the facts and accuracy of the data, opinions, and conclusions presented herein. The contents may not reflect the views of the funding agency or other individuals. The authors would like to acknowledge the financial support provided by the Georgia Department of Transportation for this study.
References
Burgess, C. P., I. Higgins, A. Pal, L. Matthey, N. Watters, G. Desjardins, and A. Lerchner. 2018. “Understanding disentangling in β-VAE.” Preprint, submitted April 10, 2018. https://arxiv.org/abs/1804.03599.
Chen, R. T. Q., Y. Rubanova, J. Bettencourt, and D. Duvenaud. 2018a. “Neural ordinary differential equations.” Preprint, submitted June 19, 2018. https://arxiv.org/abs/1806.07366.
Chen, T. Q., X. Li, R. B. Grosse, and D. Duvenaud. 2018b. “Isolating sources of disentanglement in variational autoencoders.” Preprint, submitted February 14, 2018. https://arxiv.org/abs/1802.04942.
Chen, X., Y. Duan, R. Houthooft, J. Schulman, I. Sutskever, and P. Abbeel. 2016. “InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets.” Preprint, submitted June 12, 2016. https://arxiv.org/abs/1606.03657.
Chen, Y., B. Yang, and J. Dong. 2006. “Time-series prediction using a local linear wavelet neural network.” Neurocomputing 69 (4): 449–465. https://doi.org/10.1016/j.neucom.2005.02.006.
Chorzepa, M., S. Kim, S. Durham, and A. Sinha. 2020. Development of weigh-in-motion data quality control algorithms and procedures, 18–36. Atlanta: Georgia DOT.
Donahue, J., P. Krähenbühl, and T. Darrell. 2016. “Adversarial feature learning.” Preprint, submitted May 31, 2016. https://arxiv.org/abs/1605.09782.
Dumoulin, V., I. Belghazi, B. Poole, O. Mastropietro, A. Lamb, M. Arjovsky, and A. Courville. 2016. “Adversarially learned inference.” Preprint, submitted June 2, 2016. https://arXiv.org/abs/1606.00704.
Eckmann, J. P., S. Kamphorst, and D. Ruelle. 1987. “Recurrence plots of dynamical systems.” Europhys. Lett. 4 (9): 973–977. https://doi.org/10.1209/0295-5075/4/9/004.
Funahashi, K., and Y. Nakamura. 1993. “Approximation of dynamical systems by continuous time recurrent neural networks.” Neural Netw. 6 (6): 801–806. https://doi.org/10.1016/S0893-6080(05)80125-X.
GDOT (Georgia Department of Transportation). 2020. “Traffic analysis and data application.” Accessed July 10, 2020. https://gdottrafficdata.drakewell.com/publicmultinodemap.asp.
Gong, D., L. Liu, V. Le, B. Saha, M. R. Mansour, S. Venkatesh, and A. van den Hengel. 2019. “Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection.” Preprint, submitted April 5, 2019. https://arxiv.org/abs/1904.02639.
Goswami, B. 2019. “A brief introduction to nonlinear time series analysis and recurrence plots.” Vibration 2 (4): 332–368. https://doi.org/10.3390/vibration2040021.
Hasani, R. M., M. Lechner, A. Amini, D. Rus, and R. Grosu. 2018. “Liquid time-constant recurrent neural networks as universal approximators.” Preprint, submitted November 1, 2018. https://arXiv.org/abs/1811.00321.
Higgins, I., L. Matthey, A. Pal, C. P. Burgess, X. Glorot, M. Botvinick, S. Mohamed, and A. Lerchner. 2017. “beta-VAE: Learning basic visual concepts with a constrained variational framework.” In Proc., ICLR 2017: Int. Conf. Learning Representations. La Jolla, CA: International Conference on Representation Learning.
Jiang, X., and H. Adeli. 2005. “Dynamic wavelet neural network model for traffic flow forecasting.” J. Transp. Eng. 131 (10): 771–779. https://doi.org/10.1061/(ASCE)0733-947X(2005)131:10(771).
Karras, T., S. Laine, and T. Aila. 2020. “A style-based generator architecture for generative adversarial networks.” IEEE Trans. Pattern Anal. Mach. Intell. 43 (12): 4217–4228. https://doi.org/10.1109/TPAMI.2020.2970919.
Kim, H., and A. Mnih. 2018. “Disentangling by factorising. International conference on machine learning, 2018.” Preprint, submitted February 16, 2018. https://arxiv.org/abs/1802.05983.
Kingma, D. P., and M. Welling. 2014. “Auto-encoding variational Bayes. 2nd international conference on learning representations (ICLR2014).” Preprint, submitted December 23, 2013. https://arXiv.org/abs/1312.6114v10.
Kumar, S. V., and L. Vanajakshi. 2015. “Short-term traffic flow prediction using seasonal ARIMA model with limited input data.” Eur. Transp. Res. Rev. 7 (3): 1–9. https://doi.org/10.1007/s12544-015-0170-8.
Li, J., N. Hossain, K. Wang, and M. Zaman. 2018. Development of statewide WIM data quality control and axle load spectra and traffic volume adjustment factors for Oklahoma. SPTC15.2-04-F. Washington, DC: Southern Plains Transportation Center.
Lin, L., Y. Li, and A. Sadek. 2013. “A k nearest neighbor based local linear wavelet neural network model for on-line short-term traffic volume prediction.” Procedia Social Behav. Sci. 96 (6): 2066–2077. https://doi.org/10.1016/j.sbspro.2013.08.233.
Lu, S., Q. Zhang, G. Chen, and D. Seng. 2021. “A combined method for short-term traffic flow prediction based on recurrent neural network.” Alexandria Eng. J. 60 (1): 87–94. https://doi.org/10.1016/j.aej.2020.06.008.
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.
Min, X., J. Hu, and Z. Zhang. 2010. “Urban traffic network modeling and short-term traffic flow forecasting based on GSTARIMA model.” In Proc., 13th Int. IEEE Conf. on Intelligent Transportation Systems, 1535–1540. New York: IEEE.
Razavi, A., A. van den Oord, and O. Vinyals. 2019. “Generating diverse high-fidelity images with VQ-VAE-2.” In Vol. 32 of Advances in neural information processing systems, 14837–14847. Los Angeles: NIPS Foundation.
Salimans, T., A. Karpathy, X. Chen, and D. P. Kingma. 2017. “PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications.” Preprint, submitted January 19, 2017. https://arxiv.org/abs/1701.05517.
van den Oord, A., N. Kalchbrenner, O. Vinyals, L. Espeholt, A. Graves, and K. Kavukcuoglu. 2016. “Conditional image generation with PixelCNN decoders.” In Vol. 29 of Proc., 30th Int. Conf. on Neural Information Processing Systems NIPS’16, 4797–4805. San Diego: Neural Information Processing Systems.
van den Oord, A., O. Vinyals, and K. Kavukcuoglu. 2017. “Neural discrete representation learning.” In Vol. 30 of Advances in neural information processing systems, 6306–6315. Red Hook, NY: Curran Associates.
Wiegand, K. 2018. Georgia’s traffic monitoring guide. Atlanta: Georgia DOT.
Yang, Y., H. Yanga, and Y. Fan. 2019. “Networked sensor data error estimation.” Transp. Res. Part B 122 (0191–2615): 20–39. https://doi.org/10.1016/j.trb.2019.01.013.
Zhang, C., S. Li, H. Zhang, and Y. Chen. 2020 “VELC: A new variational autoencoder based model for time series anomaly detection.” Preprint, submitted July 3, 2019. https://arXiv.org/abs/1907.01702.
Zheng, J., and M. Huang. 2020. “Traffic flow forecast through time series analysis based on deep learning.” IEEE Access 8 (Apr): 82562–82570. https://doi.org/10.1109/ACCESS.2020.2990738.
Information & Authors
Information
Published In
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Sep 20, 2021
Accepted: Dec 28, 2021
Published online: Mar 10, 2022
Published in print: May 1, 2022
Discussion open until: Aug 10, 2022
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.
Cited by
- Yongcan Huang, Jidong J. Yang, Symmetric contrastive learning for robust fault detection in time-series traffic sensor data, International Journal of Data Science and Analytics, 10.1007/s41060-024-00521-0, (2024).
- Yuanhang Chen, Shaofang Wu, Framework of Active Obstacle Avoidance for Autonomous Vehicle Based on Hybrid Soft Actor-Critic Algorithm, Journal of Transportation Engineering, Part A: Systems, 10.1061/JTEPBS.0000772, 149, 4, (2023).
- Yongcan Huang, Jidong J. Yang, Semi-supervised multiscale dual-encoding method for faulty traffic data detection, Applied Computing and Intelligence, 10.3934/aci.2022006, 2, 2, (99-114), (2022).
- Ananta Sinha, Mi G. Chorzepa, Jidong J. Yang, Sung-Hee Sonny Kim, Stephan Durham, Deep-Learning-Based Temporal Prediction for Mitigating Dynamic Inconsistency in Vehicular Live Loads on Roads and Bridges, Infrastructures, 10.3390/infrastructures7110150, 7, 11, (150), (2022).