Traffic System Anomaly Detection using Spatiotemporal Pattern Networks



Published Nov 19, 2020
Tingting Huang Chao Liu Anuj Sharma Soumik Sarkar


Traffic dynamics in the urban interstate system are critical in terms of highway safety and mobility. This paper proposes a systematic data mining technique to detect traffic system-level anomalies in a batch-processing fashion. Built on the concepts of symbolic dynamics, a spatiotemporal pattern network (STPN) architecture is developed to capture the system characteristics. This novel spatiotemporal graphical modeling approach is shown to be able to extract salient time series features and discover spatial and temporal patterns for a traffic system. An information-theoretic metric is used to quantify the causal relationships between sub-systems. By comparing the structural similarity of the information-theoretic metrics of the STPNs learnt from each day, a day with anomalous system characteristics can be identified. A case study is conducted on an urban interstate in Iowa, USA, with 11 roadside radar sensors collecting 20-second resolution speed and volume data. After applying the proposed methods on one-month data (Feb. 2017), several system-level anomalies are detected. The potential causes that include inclement weather condition and non-recurring congestion are also verified to demonstrate the efficacies of the proposed technique. Compared to the traditional predefined performance measures for the traffic systems, the proposed framework has advantages in capturing spatiotemporal features in a fast and scalable manner.

Abstract 23 | PDF Downloads 17



anomaly detection, Traffic system health monitoring, spatiotemporal pattern network

Abdulhai, B., & Ritchie, S. G. (1999). Enhancing the universality and transferability of freeway incident detection using a Bayesian-based neural network. Transportation Research Part C: Emerging Technologies, 7(5), 261–280. doi:10.1016/S0968-090X(99)00022-4
Adeli, H., & Karim, A. (2000). Fuzzy-wavelet RBFNN model for freeway incident detection. Journal of Transportation Engineering, 126(6), 464–471. doi:10.1061/(ASCE)0733-947X(2000)126:6(464)
Chakraborty, P., Hess, J. R., Sharma, A., & Knickerbocker, S. (2017). Outlier mining based traffic incident detection using big data analytics. Presented at the Transportation Research Board 96th Annual Meeting, January 8-12, Washington, D.C. Retrieve from
Jiang, Z., & Sarkar, S. (2015). Understanding wind turbine interactions using spatiotemporal pattern network. Proceedings of the ASME 2015 Dynamic Systems and Control Conference, October 28-30, Columbus, OH, USA. doi:10.1115/DSCC2015-9784
Jiang, Z., Liu, C., Akintayo, A., Henze, G., & Sarkar, S. (2017). Energy prediction using spatiotemporal pattern networks. Applied Energy, 206, 1022-1039. doi:10.1016/j.apenergy.2017.08.225
Jin, J., & Ran, B. (2009). Automatic freeway incident detection based on fundamental diagrams of traffic flow. Transportation Research Record: Journal of the Transportation Research Board, 2099, 65–75. doi:10.3141/2099-08
Jin X., Sarkar, S., Mukherjee, K., & Ray, A. (2009) Suboptimal partitioning of time-series data for anomaly detection, Proceedings of Conference on Decision and Control, December 15-18, Shanghai, China. doi:10.1109/CDC.2009.5400158
Kim, J., & Wang, G. (2016). Diagnosis and prediction of traffic congestion on urban road networks using Bayesian networks. Transportation Research Record: Journal of the Transportation Research Board, 2595, 108–118. doi:10.3141/2595-12
Li, L., He, S., Zhang, J., & Yang, F. (2016). Bagging-SVMs algorithm-based traffic incident detection. Proceedings of the 16th COTA International Conference of Transportation Professionals, July 6-9, Shanghai, China. doi:10.1061/9780784479896.132
Liu, C., Ghosal, S., Jiang, Z., & Sarkar, S. (2017). An unsupervised anomaly detection approach using energy-based spatiotemporal graphical modeling. Cyber-Physical Systems, 3(1-4), 66-102. doi:10.1080/23335777.2017.1386717
Liu, C., Gong, Y., Laflamme, S., Phares, B., & Sarkar, S. (2017). Bridge damage detection using spatiotemporal patterns extracted from dense sensor network. Measurement Science and Technology, 28(1), 014011. doi:10.1088/1361-6501/28/1/014011
Liu, C., Huang, B., Zhao, M., Sarkar, S., Vaidya, U., & Sharma, A. (2016). Data driven exploration of traffic network system dynamics using high resolution probe data. Proceedings of 2016 IEEE 55th Conference on Decision and Control (7629–7634), December 12-14, Las Vegas, NV, USA. doi:10.1109/CDC.2016.7799448
Liu, C., Jiang, D., & Yang, W. (2014). Global geometric similarity scheme for feature selection in fault diagnosis. Expert Systems with Applications, 41(8), 3585–3595. doi:10.1016/j.eswa.2013.11.037
Margreiter, M. (2016). Automatic incident detection based on bluetooth detection in northern Bavaria. Transportation Research Procedia, 15, 525–536. doi:10.1016/j.trpro.2016.06.044
Rao, C., Ray, A., Sarkar, S., & Yasar, M. (2009). Review and comparative evaluation of symbolic dynamic filtering for detection of anomaly patterns. Signal, Image and Video Processing, 3(2), 101–114. doi:10.1007/s11760-008-0061-8
Ritchie, S. G., & Cheu, R. L. (1993). Simulation of freeway incident detection using artificial neural networks. Transportation Research Part C: Emerging Technologies, 1(3), 203–217. doi:10.1016/S0968-090X(13)80001-0
Sarkar, S., Sarkar, S., Virani, N., Ray, A., & Yasar, M. (2014). Sensor fusion for fault detection and classification in distributed physical processes. Frontiers in Robotics and AI, 1, 16. doi:10.3389/frobt.2014.00016
Sarkar, S., & Srivastav, A. (2016). A composite discretization scheme for symbolic identification of complex systems. Signal Processing, 125, 156–170. doi:10.1016/j.sigpro.2016.01.018
Sarkar, S., Srivastav, A., & Shashanka, M. (2013). Maximally bijective discretization for data-driven modeling of complex systems. Proceedings of Americal Control Conference (2674–2679). June 17-19, Washington D.C., USA. doi:10.1109/ACC.2013.6580238
Solo, V. (2008). On causality and mutual information. Proceedings of 2008 47th IEEE Conference on Decision and Control (4939–4944). December 9-11, Cancun, Mexico. doi:10.1109/CDC.2008.4738640
Tang, S., & Gao, H. (2005). Traffic-incident detectionalgorithm based on nonparametric regression. IEEE Transactions on Intelligent Transportation Systems, 6(1), 38–42. doi:10.1109/TITS.2004.843112
Transportation Research Board (TRB). (2000). HCM: highway capacity manual. Washington, D.C., USA: Transportation Research Board.
Wang, Z., Bovik, A., Sheikh, H., & Simoncelli, P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600-612. doi: 10.1109/TIP.2003.819861
Weather Underground (2017, October 10). Weather history for KDSM. Retrieved from:
Wibral, M., Rahm, B., Rieder, M., Lindner, M., Vicente, R., & Kaiser, J. (2011). Transfer entropy in magnetoencephalographic data: Quantifying information flow in cortical and cerebellar networks. Progress in biophysics and molecular biology, 105(1), 80–97. doi:10.1016/j.pbiomolbio.2010.11.006
Wu, L., Liu, C., Huang, T., Sharma, A., & Sarkar, S. (2017). Traffic sensor health monitoring using spatiotemporal graphical modeling. Proceedings of the 2nd ACM SIGKDD Workshop on Machine Learning for Prognostics and Health Management, August 13-17, Halifax, Nova Scotia, Canada.
Yao, B., Hu, P., Zhang, M., & Jin, M. (2014). A support vector machine with the tabu search algorithm for freeway incident detection. International Journal of Applied Mathematics and Computer Science, 24(2), 397–404. doi: 10.2478/amcs-2014-0030
Yuan, F., & Cheu, R. L. (2003). Incident detection using support vector machines. Transportation Research Part C: Emerging Technologies, 11(3), 309–328. doi: 10.1016/S0968-090X(03)00020-2
Technical Papers