Abstract
Automatic incident detection (AID) aims to programatically detect vehicle traffic incidents from real-time traffic data, and improvements in AID are vital for future technology such as smart-city traffic planning. In this research we use a simple machine learning model (AdaBoost) applied to freely available traffic data from the Caltrans Performance Measurement System (PeMS) to develop a state of the art AID mechanism. In addition we discuss related work in AID to date, introduce and explore the data we use in our experiments, present our methods and results, and discuss conclusions and future work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Peng, H., Bobade, S.U., Cotterell, M.E., Miller, J.A.: Forecasting traffic flow: short term, long term, and when it rains. In: Chin, F.Y.L., Chen, C.L.P., Khan, L., Lee, K., Zhang, L.-J. (eds.) BIGDATA 2018. LNCS, vol. 10968, pp. 57–71. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-94301-5_5
Peng, H., Klepp, N., Toutiaee, M., Arpinar, I.B., Miller, J.A.: Knowledge and situation-aware vehicle traffic forecasting. In: 2019 IEEE International Conference on Big Data (Big Data), pp. 3803–3812. IEEE (2019)
Popescu, O., Sha-Mohammad, S., Abdel-Wahab, H., Popescu, D.C., El-Tawab, S.: Automatic incident detection in intelligent transportation systems using aggregation of traffic parameters collected through V2I communications. IEEE Intell. Transp. Syst. Mag. 9(2), 64–75 (2017)
Iqbal, Z., Khan, M.I.: Automatic incident detection in smart city using multiple traffic flow parameters via v2x communication. Int. J. Distrib. Sens. Netw. 14(11), 1550147718815845 (2018)
Karatsoli, M., Margreiter, M., Spangler, M.: Bluetooth-based travel times for automatic incident detection-a systematic description of the characteristics for traffic management purposes. Transp. Res. Procedia 24, 204–211 (2017)
Margreiter, M.: Automatic incident detection based on bluetooth detection in Northern Bavaria. Transp. Res. Procedia 15, 525–536 (2016)
Levy, B., Haddad, J., Dalyot, S.: Automatic incident detection along freeways using spatiotemporal bluetooth data. In: 15th International Conference on Location-Based Services, p. 153 (2019)
Kim, D.: Deep learning neural networks for automatic vehicle incident detection. Asia Pac. J. Convergent Res. Interchange 4(3), 119–128 (2018)
Lee, K.B., Shin, H.S., Kim, D.G.: Development of a deep-learning based automatic tracking of moving vehicles and incident detection processes on tunnels. J. Korean Tunn. Undergr. Space Assoc. 20(6), 1161–1175 (2018)
Shin, H.S., Kim, D.G., Yim, M.J., Lee, K.B., Oh, Y.S.: A preliminary study for development of an automatic incident detection system on CCTV in tunnels based on a machine learning algorithm. J. Korean Tunn. Undergr. Space Assoc. 19(1), 95–107 (2017)
Jin, X., Cheu, R.L., Srinivasan, D.: Development and adaptation of constructive probabilistic neural network in freeway incident detection. Transp. Res. Part C Emerg. Technol. 10(2), 121–147 (2002)
Rossi, R., Gastaldi, M., Gecchele, G.: Automatic incident detection on freeway ramp junctions. A fuzzy logic-based system using loop detector data. In: Żak, J., Hadas, Y., Rossi, R. (eds.) EWGT/EURO -2016. AISC, vol. 572, pp. 370–383. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-57105-8_18
Chen, L., Xu, P., Ren, T., Chen, Y., Zhou, B., Lv, H.: A SVM-based approach for VANET-based automatic incident detection. Int. J. Simul. Syst. Sci. Technol. 17(30), 1–5 (2016)
Li, M., Chen, S., Lao, Y.: Automatic incident detection algorithm based on under-sampling for imbalanced traffic data. In: Green Building, Environment, Energy and Civil Engineering: Proceedings of the 2016 International Conference on Green Building, Materials and Civil Engineering, GBMCE 2016, Hong Kong, PR China, 26–27 April 2016, p. 145. CRC Press (2016)
Lemaître, G., Nogueira, F., Aridas, C.K.: Imbalanced-learn: a Python toolbox to tackle the curse of imbalanced datasets in machine learning. J. Mach. Learn. Res. 18(17), 1–5 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Sterling, N., Miller, J.A. (2020). Traffic Incident Detection from Massive Multivariate Time-Series Data. In: Yang, Y., Yu, L., Zhang, LJ. (eds) Cognitive Computing – ICCC 2020. ICCC 2020. Lecture Notes in Computer Science(), vol 12408. Springer, Cham. https://doi.org/10.1007/978-3-030-59585-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-59585-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59584-5
Online ISBN: 978-3-030-59585-2
eBook Packages: Computer ScienceComputer Science (R0)