Learning Classifier Systems for Road Traffic Congestion Detection

Matthias Sommer, Jörg Hähner


The increase in mobility leads to a higher number of kilometres driven per vehicle and more delay due to congestion which poses a recent and future problem. Congestion generates growing environmental pollution and more car accidents. We apply machine learning concepts to the task of congestion detection in road traffic. We focus on the extended classifier system XCSR, an evolutionary rule-based on-line learning classifier system. Experiments with real-world detector data demonstrate high accuracy of XCSR for congestion detection on interstates.


  1. Alpaydin, E. (2008). Maschinelles Lernen. Oldenbourg.
  2. Ben-Hur, A. and Weston, J. (2010). Data Mining Techniques for the Life Sciences, chapter A User's Guide to Support Vector Machines, pages 223-239. Humana Press.
  3. Bordes, A., Ertekin, S., Weston, J., and Bottou, L. (2005). Fast kernel classifiers with online and active learning. Journal of Machine Learning Research, 6:1579-1619.
  4. Brumback, T. E. (2009). A Mathematical Model for Freeway Incident Detection and Characterization: A Fuzzy Approach. PhD thesis, University of Alabama.
  5. Bull, L., editor (2004). Applications of Learning Classifier Systems. Springer.
  6. Bull, L. and Kovacs, A. (2005). Foundations of Learning Classifier Systems , volume 183, chapter Foundations of Learning Classifier Systems: An Introduction, pages 1-17. Springer.
  7. Bull, L., Sha'Aban, J., Tomlinson, A., Addison, J. D., and Heydecker, B. (2004). Towards distributed adaptive control for road traffic junction signals using learning classifier systems. In Applications of Learning Classifier Systems , pages 276-299. Springer.
  8. Butz, M. and Wilson, S. (2002). An algorithmic description of XCS. Soft Computing - A Fusion of Foundations, Methodologies and Applications, 6:144 - 153.
  9. Deniz, O., Celikoglu, H. B., and Gurcanli, G. E. (2012). Overview to some incident detection algorithms: A comparative evaluation with istanbul freeway data. Proc. of 12th Int. Conf. Reliability and Statistics in Transportation and Communication, pages 274-284.
  10. Diamantopoulos, T., Kehagias, D., Knig, F. G., and Tzovaras, D. (2014). Use of density-based cluster analysis and classification techniques for traffic congestion prediction and visualisation. In Transp. Research Arena Proceedings.
  11. Ertekin, S., Bottou, L., and Giles, C. (2011). Nonconvex online support vector machines. IEEE Trans. on Pattern Analysis and Machine Intelligence, 33(2):368-381.
  12. Holland, J. H. (1986). A mathematical framework for studying learning in classifier systems. Phys. D, 2(1- 3):307-317.
  13. Hsu, C.-W. and Lin, C.-J. (2002). A comparison of methods for multiclass support vector machines. Trans. Neural Networks, 13(2):415-425.
  14. James, G., Witten, D., Hastie, T. J., and Tibshirani, R. J. (2013). An Introduction to Statistical Learning. Springer.
  15. Klejnowski, L. (2008). Design and implementation of an algorithm for the detection of disturbances in traffic networks. Master's thesis, University of Hannover, Institute for Systems Engineering.
  16. Lenz, B., Nobis, C., K öhler, K., Mehlin, M., Follmer, R., Gruschwitz, D., Jesske, B., and Quandt, S. (2010). Mobilität in Deutschland 2008. DLRForschungsbericht.
  17. Liu, Q., Lu, J., Chen, S., and Zhao, K. (2014). Multiple naïve Bayes classifiers ensemble for traffic incident detection. Mathematical Problems in Engineering, 2014.
  18. Mahmassani, H. S., Haas, C., Zhou, S., and Peterman, J. (1999). Evaluation of incident detection methodologies. Technical report, Center for Transportation Research, University of Texas.
  19. Ozbay, K. and Kachroo, P. (1999). Incident Management in Intelligent Transportation Systems. Artech House ITS library. Artech House.
  20. Parkany, E. and Xie, P. C. (2005). A complete review of incident detection algorithms & their deployment: What works and what doesn't. Technical report, Fall River, MA: New England Transp. Consortium.
  21. Picard, D., Thome, N., and Cord, M. (2013). Jkernelmachines: a simple framework for kernel machine. Journal of Machine Learning Research, 14(1):1417-1421.
  22. Prothmann, H., Rochner, F., Tomforde, S., Branke, J., M üller-Schloer, C., and Schmeck, H. (2008). Organic control of traffic lights. In Proc. of the 5th Int. Conf. on Autonomic and Trusted Computing, volume 5060 of LNCS, pages 219-233. Springer.
  23. Schrank, D., Eisele, B., and Lomax, T. (2012). 2012 Urban mobility report. Texas A&M Transp. Institute. http://mobility.tamu.edu/ums/.
  24. Shalev-Shwartz, S. and Zhang, T. (2013). Stochastic dual coordinate ascent methods for regularized loss. Journal of Machine Learning Research, 14(1):567-599.
  25. S?ingliar, T. and Hauskrecht, M. (2006). Towards a learning incident detection system. In Proc. of the Workshop on Machine Learning for Surveillance and Event Detection at the 23rd Int. Conf. on Machine Learning.
  26. Srinivasan, D., Jin, X., and Cheu, R. L. (2004). Evaluation of adaptive neural network models for freeway incident detection. In IEEE Transaction on Intelligent Transp. Systems, volume 5, pages 1-11.
  27. Wilson, S. (2000). Get real! xcs with continuous-valued inputs. In Learning Classifier Systems , volume 1813 of LNCS, pages 209-219. Springer.
  28. Yang, X., Sun, Z., and Sun, Y. (2004). A freeway traffic incident detection algorithm based on neural networks. In Yin, F.-L., Wang, J., and Guo, C., editors, Advances in Neural Networks - ISNN 2004, volume 3174 of LNCS, pages 912-919. Springer.
  29. Zhang, K. and Xue, G. (2010). A real-time urban traffic detection algorithm based on spatio-temporal OD matrix in vehicular sensor network. Wireless Sensor Network, 2(9):668-674.

Paper Citation

in Harvard Style

Sommer M. and Hähner J. (2017). Learning Classifier Systems for Road Traffic Congestion Detection . In Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-242-4, pages 142-150. DOI: 10.5220/0006214101420150

in Bibtex Style

author={Matthias Sommer and Jörg Hähner},
title={Learning Classifier Systems for Road Traffic Congestion Detection},
booktitle={Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},

in EndNote Style

JO - Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Learning Classifier Systems for Road Traffic Congestion Detection
SN - 978-989-758-242-4
AU - Sommer M.
AU - Hähner J.
PY - 2017
SP - 142
EP - 150
DO - 10.5220/0006214101420150