Machine Learning Framework for Improving Accuracy of Probe Speed Data
Publication: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 7, Issue 2
Abstract
A tremendous potential exists for using probe data to support various traffic operations activities. However, limited real-time probe data, especially on arterial roads, have become a barrier to realizing the full potential of this technology. In the absence of real-time probe data, traffic speeds are estimated via prediction engines trained on historical data. The accuracy of such traditional speed estimation approaches could be significantly improved if real-time data available through nearby infrastructure-mounted (IM) sensors were incorporated in the prediction process. This paper develops a machine learning framework for generating probe-like speed data from IM sensors with the aim of improving the accuracy of probe speed data during periods of low probe penetration. The framework includes using a pattern recognition system for extracting trends from historical traffic speed data. The extracted patterns together with historical temporal traffic flow data are used to prepare a representative training set for a deep learning–based model that can transform IM sensor data into probe-like data. The proposed approach successfully generated pseudo-probe data sets from nearby IM sensors with about 4.8 and mean absolute error on freeways and arterials, respectively. A comparative analysis with baseline methods proved the superiority of the methodology adopted.
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 generated or used during the study are available in a repository online (Adu-Gyamf 2019), in accordance with funder data retention policies.
References
Abadi, M., et al. 2016. “Tensorflow: A system for large-scale machine learning.” In Proc., Symp. on Operating Systems Design and Implementation, 265–283. Berkeley, CA: The Advanced Computing Systems Association.
Adu-Gyamf, Y. O. 2019. “LSTM probe speed prediction.” Accessed August 8, 2012. https://github.com/TITAN-lab/LSTM-PredictProbeSpeed.
Adu-Gyamfi, Y. O., N. O. Attoh Okine, and A. Y. Ayenu-Prah. 2010. “Critical analysis of different Hilbert-Huang algorithms for pavement profile evaluation.” J. Comput. Civ. Eng. 24 (6): 514–524. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000056.
Adu-Gyamfi, Y. O., A. Sharma, S. Knickerbocker, N. Hawkins, and M. Jackson. 2017. “Framework for evaluating the reliability of wide-area probe data.” Transp. Res. Rec. 2643 (1): 93–104. https://doi.org/10.3141/2643-11.
Adu-Gyamfi, Y. O., and M. Zhao. 2018. “Traffic speed prediction for urban arterial roads using deep neural networks.” In Proc., Int. Conf. on Transportation and Development. Reston, VA: ASCE. https://doi.org/10.1061/9780784481547.009.
Ahsani, V., M. Amin-Naseri, S. Knickerbocker, and A. Sharma. 2018. “Quantitative analysis of probe data characteristics: Coverage, speed bias and congestion detection precision.” J. Intell. Transp. Syst. 23 (3): 1–17. https://doi.org/10.1080/15472450.2018.1502667.
Asare, S. K., Y. Adu-Gyamfi, N. Attoh-Okine, and H. Park. 2013. “Adaptive freeway incident detection algorithm using the Hilbert-Huang transform.” In Proc., Transportation Research Board 92nd Annual Meeting. Washington, DC: Transportation Research Board.
Attoh-Okine, N., Y. Adu-Gyamfi, and S. Mensah. 2011. “Potential application of hybrid belief functions and Hilbert-Huang transform in layered sensing.” IEEE Sensors J. 11 (3): 530–535. https://doi.org/10.1109/JSEN.2010.2048021.
Bachmann, C. 2011. “Multi-sensor data fusion for traffic speed and travel time estimation.” Doctoral dissertation, Dept. of Civil Engineering, Univ. of Toronto.
Bhavik, R. B. 1999. “Multiscale analysis and modeling using wavelets.” J. Chemom. 13 (3–4): 415–434. https://doi.org/10.1002/(SICI)1099-128X(199905/08)13:3/4%3C415::AID-CEM544%3E3.0.CO;2-8.
Cheu, R. L., D. H. Lee, and C. Xie. 2001. “An arterial speed estimation model fusing data from stationary and mobile sensors.” In Proc., Intelligent Transportation Systems, 573–578. New York: IEEE. https://doi.org/10.1109/ITSC.2001.948723.
Chollet, F. 2017. “Keras.” Accessed June 18, 2020. https://github.com/fchollet/keras.
Coifman, B., and S. Kim. 2013. Assessing the performance of the SpeedInfo sensor. Columbus, OH: Ohio Dept. of Transportation.
Garber, N., and L. Hoel. 2002. Traffic and highway engineering. 3rd ed. Pacific Grove, CA: Brooks/Cole.
Guo, J., Y. Luo, and K. Li. 2017. “An adaptive hierarchical trajectory following control approach of autonomous four-wheel independent drive electric vehicles.” IEEE Trans. Intell. Transp. Syst. 19 (8): 2482–2492. https://doi.org/10.1109/TITS.2017.2749416.
Gutierrez, M. A., J. A. Florez, and S. T. Kofuji. 2013. “Kalman filter and ARMA filter as approach to multiple sensor data fusion problem.” In Vol. 1 of Proc., 47th Int. Carnahan Conf. on Security Technology (ICCST), 8–11. New York: IEEE. https://doi.org/10.1109/CCST.2013.6922059.
He, S., Y. Cheng, G. Zhong, and B. Ran. 2017. “A data-driven study on the sample size of cellular handoff probe system.” Adv. Mech. Eng. 9 (4). https://doi.org/10.1177/1687814017698442.
Huang, N. E., Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, N.-C. Yen, C. C. Tung, and H. H. Liu. 1998. “The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis.” Proc. R. Soc. London, Ser. A 454 (1971): 903–995. https://doi.org/10.1098/rspa.1998.0193.
Jia, C., Q. Li, S. Oppong, D. Ni, J. Collura, and P. W. Shuldiner. 2013. “Evaluation of alternative technologies to estimate travel time on rural interstates.” In Proc., 92nd Annual Meeting of the Transportation Research Board. Washington, DC: Transportation Research Board.
Kim, K., S. I. J. Chien, and L. N. Spasovic. 2011. “Evaluation of technologies for freeway travel time estimation: Case study of I-287 in New Jersey.” In Proc., 90th Annual Meeting of the Transportation Research Board. Washington, DC: Transportation Research Board.
Lattimer, C., and G. Glotzbach. 2012. “Evaluation of third party travel time data.” In Proc., 22nd Annual ITS America’s Meeting and Exposition. Washington, DC: Intelligent Transportation Society of America.
Lint, H. 2004. Reliable travel time prediction for freeways. Delft, Netherlands: Netherlands TRAIL Research School.
Niu, X., X. Wu, P. Xie, and L. Pan. 2014. “A time-frequency analysis of event-related desynchronization/synchronization based on Gabor filter.” In Proc., 11th World Congress on Intelligent Control and Automation, 5179–5184. New York: IEEE. https://doi.org/10.1109/WCICA.2014.7053596.
Rakha, H., and W. Zhang. 2005. “Estimating traffic stream space mean speed and reliability from dual-and single-loop detectors.” Transp. Res. Rec. 1925 (1): 38–47. https://doi.org/10.1177/0361198105192500105.
Salvador, S., and P. Chan. 2004. FastDTW: Toward accurate dynamic time warping in linear time and space. Seattle: KDD Workshop on Mining Temporal and Sequential Data.
Shvachko, K., H. Kuang, S. Radia, and R. Chansler. 2010. “The Hadoop distributed file system.” In Proc., 26th Symp. on Mass Storage Systems and Technologies (MSST), 1–10. New York: IEEE. https://doi.org/10.1109/MSST.2010.5496972.
Soriguera, F., and F. Robusté. 2011. “Estimation of traffic stream space mean speed from time aggregations of double loop detector data.” Transp. Res. Part C: Emerging Technol. 19 (1): 115–129. https://doi.org/10.1016/j.trc.2010.04.004.
Wardrop, J. G. 1952. “Road paper. Some theoretical aspects of road traffic research.” Proc. Inst. Civ. Eng. 1 (3): 325–362.
Williams, B. M., and L. A. Hoel. 2003. “Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results.” J. Transp. Eng. 129 (6): 664–672. https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664).
Wu, C. H., J. M. Ho, and D. T. Lee. 2004. “Travel-time prediction with support vector regression.” IEEE Trans. Intell. Transp. Syst. 5 (4): 276–281. https://doi.org/10.1109/TITS.2004.837813.
Yue, H., E. G. Jones, and P. Revesz. 2010. “Local polynomial regression models for average traffic speed estimation and forecasting in linear constraint databases.” In Proc, 17th Int. Symp. Temporal Representation and Reasoning, 154–161. New York: IEEE. https://doi.org/10.1109/TIME.2010.24.
Yue, H., and P. Z. Revesz. 2012. “TVICS: An efficient traffic video information converting system.” In Proc., 19th Int. Symp. Temporal Representation and Reasoning (TIME), 141–148. New York: IEEE. https://doi.org/10.1109/TIME.2012.9.
Yue, H., L. R. Rilett, and P. Z. Revesz. 2016. “Spatio-temporal traffic video data archiving and retrieval system.” GeoInformatica 20 (1): 59–94. https://doi.org/10.1007/s10707-015-0231-0.
Zaharia, M., M. Chowdhury, M. J. Franklin, S. Shenker, and I. Stoica. 2010. “Spark: Cluster computing with working sets.” In Proc., 2nd USENIX Conf. on Hot Topics in Cloud Computing, 10–10. Berkeley, CA: USENIX Association.
Zhao, X., and D. Zhang. 2018. “A review of multi-sensor data fusion for traffic.” In Proc., Int. Symp. on Intelligence Computation and Applications, 432–444. Singapore: Springer.
Information & Authors
Information
Published In
ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 7 • Issue 2 • June 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Aug 12, 2020
Accepted: Nov 17, 2020
Published online: Jan 31, 2021
Published in print: Jun 1, 2021
Discussion open until: Jun 30, 2021
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.