Modeling of a Vehicle Accident Prediction System Based on a Correlation of Heterogeneous Sources

  • Pablo MarcilloEmail author
  • Lorena Isabel Barona López
  • Ángel Leonardo Valdivieso Caraguay
  • Myriam Hernández-Álvarez
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1212)


Statistics affirm that traffic accidents are the main cause of death in developing countries. The indicators are alarming, so governments, manufacturers, and researchers have been looking for solutions to mitigate them. Despite all efforts to face this problem, the number of victims remains high. A significant percentage of traffic accidents are caused by external factors, so the search for solutions that use information from multiple sources is crucial. This article presents a traffic accident prediction system based on heterogeneous sources using data mining techniques and machine learning algorithms. The development of this system includes the following tasks: collecting information from different sources, performing cluster analyses and feature selection, generating new datasets, performing machine learning algorithms to define accident rates, and sending traffic rate levels to the vehicles. For this article, we focused on performing cluster analyses to determine high-risk clusters that identify drivers with risky driving patterns.


Traffic accident prediction Heterogeneous sources High-risk clusters Machine learning Data mining 


  1. 1.
  2. 2.
  3. 3.
    Wong, C., Qidwai, U.: Vehicle collision avoidance system. In: Proceedings of IEEE Sensors, pp. 31–319. IEEE Press, Vienna (2004)Google Scholar
  4. 4.
    Ziebinski, A., Cupek, R., Grzechca, D., Chruszczyk, L.: Review of advanced driver assistance systems (ADAS). In: AIP Conference Proceedings, vol. 1906, p. 120002. AIP Publishing LLC (2017)Google Scholar
  5. 5.
    Zhang, X., Huang, F., Zheng, C.: Causes analysis of the serious road traffic accident cases. In: 2016 5th International Conference on Energy and Environmental Protection (ICEEP 2016). Atlantis Press, Beijing (2016)Google Scholar
  6. 6.
    Xiong, X., Chen, L., Liang, J.: A new framework of vehicle collision prediction by combining SVM and HMM. IEEE Trans. Intell. Transp. Syst. 19, 699–710 (2018)CrossRefGoogle Scholar
  7. 7.
    Ren, H., Song, Y., Wang, J., Hu, Y., Lei, J.: A deep learning approach to the citywide traffic accident risk prediction. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3346–3351. IEEE Press (2018)Google Scholar
  8. 8.
    Park, S., Kim, S., Ha, Y.: Highway traffic accident prediction using VDS big data analysis. J. Supercomput. 72, 2815–2831 (2016)CrossRefGoogle Scholar
  9. 9.
    Yuan, Z., Zhou, X., Yang, T.: Hetero-ConvLSTM. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining – KDD 2018, New York, pp. 98–992 (2018)Google Scholar
  10. 10.
    Santana, E., Hotz, G.: Learning a driving simulator. arXiv preprint (2016)Google Scholar
  11. 11.
    Biasini, R., Hotz, G., Khalandovsky, S., Santana, E., Van der Westhuizen, N.: The people’s comma (2016).
  12. 12.
    Pham, D., Dimov, S., Nguyen, C.: Selection of K in K-means clustering. Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci. 219, 103–119 (2005)CrossRefGoogle Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Pablo Marcillo
    • 1
    Email author
  • Lorena Isabel Barona López
    • 1
  • Ángel Leonardo Valdivieso Caraguay
    • 1
  • Myriam Hernández-Álvarez
    • 1
  1. 1.Departamento de Informática y Ciencias de la ComputaciónEscuela Politécnica NacionalQuitoEcuador

Personalised recommendations