Research on Abnormal Driving Behavior Identification of Freeway Based on XGBoost Method
Based on the vehicle track information on expressway collected by the radar on the roadside, the information on abnormal driving behavior of vehicles is analyzed. The XGBoost method is used to classify and analyze abnormal driving behaviors such as rapid acceleration, rapid deceleration, speeding, and emergency stop. From the result, the authors can see the accuracy rate in training set can reach 81.23%. Different methods such as decision tree, SVM, random forest, and GBDT are also used to analyze the same abnormal driving; the accuracy is not above 81%. The method of expressway classification warning method can provide technical support for expressway traffic safety management.
- Record URL:
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784485040
-
Supplemental Notes:
- © 2023 American Society of Civil Engineers.
-
Corporate Authors:
American Society of Civil Engineers
1801 Alexander Bell Drive
Reston, VA United States 20191-4400 -
Authors:
- Liu, Kun
- Sun, Chuanjiao
- Li, Chunyang
-
Conference:
- 23rd COTA International Conference of Transportation Professionals
- Location: Beijing , China
- Date: 2023-7-14 to 2023-7-17
- Publication Date: 2023
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: pp 284-289
- Monograph Title: CICTP 2023: Emerging Data-Driven Sustainable Technological Innovation in Transportation
Subject/Index Terms
- TRT Terms: Automobile driving; Classification; Detection and identification technologies; Driving behavior; Freeways; High risk drivers
- Identifier Terms: XGBoost (Software)
- Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Safety and Human Factors;
Filing Info
- Accession Number: 01910452
- Record Type: Publication
- ISBN: 9780784485040
- Files: TRIS, ASCE
- Created Date: Feb 29 2024 11:32AM