Towards Adaptive Sensory Data Fusion for Detecting Highway Traffic Conditions in Real Time
The key challenge of detecting highway traffic conditions is to achieve it in a fully-covered, high-accuracy, low-cost and real-time manner. We present an approach named Megrez on the basis of treating mobile phones and probe vehicles as roving sensors, loop detectors as static sensors. Megrez can admit one or multiple types of data, including signaling data in a mobile communication network, data from loop detectors, and GPS data from probe vehicles, to carry out the traffic estimation and monitoring. In order to accurately reconstruct traffic conditions with full road segment coverage, Megrez provides a practical way to overcome the sparsity and incoherence of sensory data and recover the missing data in light of recent progresses in compressive sensing. Moreover, Megrez incorporates the characteristics of traffic flows to rectify the estimates. Using large-scale real-world data as input, we conduct extensive experiments to evaluate Megrez. The experimental results show that, in contrast to three other fusion methods, the results from our approach have high precisions and recalls. In addition, Megrez keeps the errors of estimates low even when not all three types of data are available.
KeywordsData fusion Traffic condition detection Mobile signaling Compressive sensing Adaptation
This work was supported by the National Natural Science Foundation of China under Grant No. 61472408 and the Ministry of Transportation of China under Grant No. 2015315Q16080. Tingjian Ge was supported in part by the NSF grants IIS-1149417 and IIS-1633271.
- 2.Russell, T.: Signaling System 7, 6th edn. McGraw-Hill Education, New York (2014)Google Scholar
- 3.Deng, D., Shahabi, C., Demiryurek, U., Zhu, L., Yu, R., Liu, Y.: Latent space model for road networks to predict time-varying traffic. In: ACM International Conference on Knowledge Discovery and Data Mining, pp. 1525–1534 (2016)Google Scholar
- 6.Zhu, H., Zhu, Y., Li, M., Ni, L.M.: SEER: metropolitan-scale traffic perception based on lossy sensory data. In: IEEE International Conference on Computer Communications, Rio De Janeiro, Brazil, pp. 217–225 (2009)Google Scholar
- 12.Becker, R.A., Caceres, R., Hanson, K., Ji, M.L., Urbanek, S., Varshavsky, A., Volinsky, C.: Route classification using cellular handoff patterns. In: Proceedings of the 13th International Conference on Ubiquitous Computing, pp. 123–132 (2011)Google Scholar
- 15.Aslam, J., Lim, S., Pan, X., Rus, D.: City-scale traffic estimation from a roving sensor network. ACM Conference on Embedded Network Sensor Systems, pp. 141–154 (2012)Google Scholar
- 16.Bouillet, E., Chen, B., Cooper, C., Dahlem, D., Verscheure, O.: Fusing traffic sensor data for real-time road conditions. In: International Workshop on Sensing and Big Data Mining, pp. 1–6 (2013)Google Scholar
- 17.Yang, L., Pereira, F.C., Seshadri, R., O’Sullivan, A., Antoniou, C., Ben-Akiva, M.: DynaMIT2.0: architecture design and preliminary results on real-time data fusion for traffic prediction and crisis management. In: IEEE 18th International Conference on Intelligent Transportation Systems, pp. 2250–2255 (2015)Google Scholar
- 19.Bach, F.R.: Consistency of trace norm minimization. J. Mach. Learn. Res. 9(2) (2008)Google Scholar
- 20.Fazel, M.: Matrix rank minimization with applications. Ph.D. dessertation, Department of electrical engineering, Stanford University, California (2002)Google Scholar
- 22.Jblas. http://jblas.org/
- 23.Cassidy, M.J., Windover, J.R.: Methodology for assessing dynamics of freeway traffic flow. Transp. Res. Rec. 1484, 73–79 (1995)Google Scholar