Prediction method of driving risk in complex environment based on fuzzy comprehensive evaluation model

In order to solve the problems of low prediction accuracy and poor real-time prediction in traditional driving risk prediction methods of vehicle, a fuzzy comprehensive evaluation model based driving risk prediction method in complex environment is proposed. In this method, the driving sample data are filtered first, and the incomplete and unstable driving data are removed. The vehicle’s driving model is constructed with the processed data, and the force and dynamics of the vehicle’s driving model are analyzed with the particle dynamics. The risk factor analysis set is constructed, the entropy weight method is used to determine the risk factor weight, and the five level classification method is used to construct the risk assessment set according to the analysis results of the weight method. The fuzzy evaluation matrix of vehicle’s driving risk in complex environment is designed, and the risk prediction model is constructed to realize the prediction of vehicle’s driving risk in complex environment. The experimental results show that the prediction accuracy of the proposed method is as high as 0.98, and the prediction is real-time and reliable.

• Record URL:
  • http://dx.doi.org/10.4399/97888255318621
• Record URL:
  • http://www.atsinternationaljournal.com/index.php/2020-issues/special-issue-2020-vol1/1120-prediction-method-of-driving-risk-in-complex-environment-based-on-fuzzy-comprehensive-evaluation-model
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/18245463
• Supplemental Notes:
  • © 2020, Gioacchino Onorati Editore. All rights reserved.
• Authors:
  • Chen, X L
  • Jim, G J
• Publication Date: 2020

Language

• English

Media Info

• Media Type: Web
• Pagination: pp 3-12
• Serial:
  • Advances in Transportation Studies
  • Issue Number: Special Issue 1
  • Publisher: University Roma Tre
  • ISSN: 1824-5463
  • Serial URL: http://www.atsinternationaljournal.com/

Subject/Index Terms

• TRT Terms: Crash risk forecasting; Fuzzy systems; Predictive models; Traffic data; Traffic safety
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors;

Filing Info

• Accession Number: 01761042
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 22 2020 9:36AM