Driver Clustering According to the Ratio of Dangerous Behavior Using Machine Learning Algorithms

153

Abstract

The paper conducts the research of defining dangerous driving of a vehicle using signals collected during the ride. A number of modern clustering models for drivers segmentation on classes based on the ratio of dangerous driving was used. New approach of data aggregation aiming to cluster data by signal distribution histograms was developed. Achieved results could be used in commercial systems that monitor the quality of drivers behavior in retrospective.

General Information

Keywords: clustering, distribution histograms, dangerous driving, monitoring systems, machine learning

Journal rubric: Data Analysis

Article type: scientific article

DOI: https://doi.org/10.17759/mda.2022120101

Received: 04.03.2022

Accepted:

For citation: Badanina N.D., Sudakov V.A. Driver Clustering According to the Ratio of Dangerous Behavior Using Machine Learning Algorithms. Modelirovanie i analiz dannikh = Modelling and Data Analysis, 2022. Vol. 12, no. 1, pp. 5–15. DOI: 10.17759/mda.2022120101. (In Russ., аbstr. in Engl.)

References

  1. Kutukov D.S. Primenenie metodov klasterizacii dlya obrabotki novostnogo potoka // Tekhnicheskie nauki: problemy i perspektivy: materialy I Mezhdunar. nauch. konf. Sankt-Peterburg: Renome, 2011. pp. 77-83. (In Russ.).
  2. Dik D.I. Klasterizaciya voditelej po stilyam tormozheniya . Kurganskij gosudarstvennyj universitet. Vestnik KGU. 2012. №2(24). pp. 17-20. (In Russ.).
  3. Monitoring manery vozhdeniya [URL]: https://pro.yandex/ru-ru/moskva/knowledge-base/taxi/safety/monitoring-driving. (In Russ.).
  4. Jain A.K. Data clustering: 50 years beyond K-means . Pattern Recognition Letters, 31(8). 2010. pp. 651–666.
  5. Huaikun Xiang , Jiafeng Zhu , Guoyuan Liang and Yingjun Shen Prediction of Dangerous Driving Behavior Based on Vehicle Motion State and Passenger Feeling Using Cloud Model and Elman Neural Network. Frontiers in Neurorobotics. April 2021. Vol. 15. p. 16.
  6. Omerustaoglu Furkan, Sakar C. Okan, Kar Gorkem Distracted driver detection by combining in-vehicle and image data using deep learning // Applied Soft Computing 96(6). 2020.
  7. J. Hartigan Clustering Algorithms . New York: Wiley, 1975.

Information About the Authors

Natalya D. Badanina, Master Student, Moscow Aviation Institute (National Research University), Programmer, Keldysh Institute of Applied Mathematics (Russian Academy of Sciences), Moscow, Russia, ORCID: https://orcid.org/0000-0002-5301-1526, e-mail: natashabadanina99@gmail.com

Vladimir A. Sudakov, Doctor of Engineering, Professor of Department 805, Moscow Aviation Institute (MAI), Leading Researcher, Keldysh Institute of Applied Mathematics (Russian Academy of Sciences), Moscow, Russia, ORCID: https://orcid.org/0000-0002-1658-1941, e-mail: sudakov@ws-dss.com

Metrics

Views

Total: 370
Previous month: 15
Current month: 12

Downloads

Total: 153
Previous month: 2
Current month: 1