Abstract
Many deployed traffic incident detection systems use algorithms that require significant manual tuning. We seek machine learning incident detection solutions that reduce the need for manual adjustments by taking advantage of massive databases of traffic sensor network measurements. First, we show that a rather straightforward supervised learner based on the SVM model outperforms a fixed detection model used by state-of-the-art traffic incident detectors. Second, we seek further improvements of learning performance by correcting misaligned incident times in the training data. The misalignment is due to an imperfect incident logging procedure. We propose a label realignment model based on a dynamic Bayesian network to re-estimate the correct position (time) of the incident in the data. Training on the automatically realigned data consistently leads to improved detection performance in the low false positive region.
Chapter PDF
Similar content being viewed by others
Keywords
- False Alarm Rate
- Dynamic Bayesian Network
- Incident Detection
- Highway Segment
- Conditional Gaussian Distribution
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Martin, P., Perrin, H., Hansen, B.: Incident detection algorithm evaluation. Technical Report UTL-0700-31, Utah Traffic Laboratory (July (2000)
Stephanedes, Y., Hourdakis, J.: Transferability of freeway incident detection algorithms. Technical Report Transportation Research Record 1554, Transportation Research Board, National Research Council (1996)
Dia, H., Rose, G., Snell, A.: Comparative performance of freeway automated incident detection algorithms (1996)
Rose, G., Dia, H.: Freeway automatic incident detection using artificial neural networks. In: Proceedings of the International Conference on Application of New Technology to Transport Systems, vol. 1, pp. 123–140 (1995)
Ritchie, S.G., Abdulhai, B.: Development, testing and evaluation of advanced techniques for freeway incident detection. Technical Report UCB-ITS-PWP-97-22, California Partners for Advanced Transit and Highways (PATH) (1997)
Parkanyi, E., Xie, C.: A complete review of incident detection algorithms and their deployment: What works and what doesn’t. Technical Report NETCR37, New England Transportation Consortium (2005)
Dean, T., Kanazawa, K.: A model for reasoning about persistence and causation. Computational Intelligence 5, 142–150 (1989)
Provost, F.J., Fawcett, T.: Analysis and visualization of classifier performance: Comparison under imprecise class and cost distributions. In: Knowledge Discovery and Data Mining, pp. 43–48 (1997)
Cooper, G., Dash, D., Levander, J., Wong, W.K., Hogan, W., Wagner, M.: Bayesian biosurveillance of disease outbreaks. In: UAI 2004. Proceedings of the 20th Annual Conference on Uncertainty in Artificial Intelligence, pp. 94–103. AUAI Press, Arlington, Virginia (2004)
Bach, F., Heckerman, D., Horvitz, E.: On the path to an ideal ROC curve: Considering cost asymmetry in learning classifiers. In: Cowell, R.G., Ghahramani, Z. (eds.) Proceedings of AISTATS 2005, pp. 9–16 (2005)
Mangasarian, O.L., Musicant, D.R.: Lagrangian support vector machine classification. Technical Report 00-06, Data Mining Institute, Computer Sciences Department, University of Wisconsin, Madison, Wisconsin (June 2000), ftp://ftp.cs.wisc.edu/pub/dmi/tech-reports/00-06.ps
Singliar, T., Hauskrecht, M.: Towards a learning incident detection system. In: ICML 2006 Workshop on Machine Learning Algorithms for Surveillance and Event Detection (2006)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood for incomplete data via the EM algorithm. Journal of Royal Statistical Society 39, 1–38 (1977)
Taylor, P.A.: Analysis and synthesis of intonation using the Tilt model. Journal of the Acoustical Society of America 107(3), 1697–1714 (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Šingliar, T., Hauskrecht, M. (2007). Learning to Detect Adverse Traffic Events from Noisily Labeled Data. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladenič, D., Skowron, A. (eds) Knowledge Discovery in Databases: PKDD 2007. PKDD 2007. Lecture Notes in Computer Science(), vol 4702. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74976-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-74976-9_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74975-2
Online ISBN: 978-3-540-74976-9
eBook Packages: Computer ScienceComputer Science (R0)