DOI QR코드

DOI QR Code

A Study on the Analysis of Bus Machine Learning in Changwon City Using VIMS and DTG Data

VIMS와 DTG 데이터를 이용한 창원시 시내버스 머신러닝 분석 연구

  • 박지양 (한국교통안전공단 첨단안전연구처) ;
  • 정재환 (한국교통안전공단 첨단안전연구처) ;
  • 윤진수 (한국교통안전공단 빅데이터센터) ;
  • 김성철 ;
  • 김지연 ;
  • 이호상 (한국교통안전공단 첨단안전연구처) ;
  • 류익희 (한국교통안전공단 자동차검사본부) ;
  • 권영문 (한국교통안전공단 첨단안전연구처)
  • Received : 2021.05.31
  • Accepted : 2021.12.20
  • Published : 2022.03.31

Abstract

Changwon City has the second highest accident rate with 79.6 according to the city bus accident rate. In fact, 250,000 people use the city bus a day in Changwon, The number of accidents is increasing gradually. In addition, a recent fire accident occurred in the engine room of a city bus (CNG) in Changwon, which has gradually expanded the public's anxiety. In the case of business vehicles, the government conducts inspections with a short inspection cycle for the purpose of periodic safety inspections, etc., but it is not in the monitoring stage. In the case of city buses, the operation records are monitored using Digital Tacho Graph (DTG). As such, driving records, methods, etc. are continuously monitored, but inspections are conducted every six months to ascertain the safety and performance of automobiles. It is difficult to identify real-time information on automobile safety. Therefore, in this study, individual automobile management solutions are presented through machine learning techniques of inspection results based on driving records or habits by linking DTG data and Vehicle Inspection Management System (VIMS) data for city buses in Changwon from 2019 to 2020.

Keywords

References

  1. 류민기, 2019, "'쾅'끊이지 않는 사고".
  2. 창원시 버스정보시스템 BIS.
  3. 최호영, 2021, "운전기사 덕분에...승객 내린 시내버스에 불 치솟아".
  4. www.nhtsa.gov
  5. Vehicle Inspection Management System Manual.
  6. Digital Tacho Graph Manual.
  7. 자동차 관리법.
  8. Kwon, A., 2013, "Variable selection using Random Forest", unpublished master's thesis, Inha University.
  9. Breiman, L., 2002, "Random forests. Machine Learning", 45(1), 5~32. https://doi.org/10.1023/A:1010933404324
  10. Davide Chicco, Giuseppe Jurman, 2020, "The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation", 21(1), ISSN 1471~2164.