DOI QR코드

DOI QR Code

Development for City Bus Dirver's Accident Occurrence Prediction Model Based on Digital Tachometer Records

디지털 운행기록에 근거한 시내버스 운전자의 사고발생 예측모형 개발

  • Received : 2016.02.11
  • Accepted : 2016.02.16
  • Published : 2016.02.28

Abstract

This study aims to develop a model by which city bus drivers who are likely to cause an accident can be figured out based on the information about their actual driving records. For this purpose, from the information about the actual driving records of the drivers who have caused an accident and those who have not caused any, significance variables related to traffic accidents are drawn, and the accuracy between models is compared for the classification models developed, applying a discriminant analysis and logistic regression analysis. In addition, the developed models are applied to the data on other drivers' driving records to verify the accuracy of the models. As a result of developing a model for the classification of drivers who are likely to cause an accident, when deceleration ($X_{deceleration}$) and acceleration to the right ($Y_{right}$) are simultaneously in action, this variable was drawn as the optimal factor variable of the classification of drivers who had caused an accident, and the prediction model by discriminant analysis classified drivers who had caused an accident at a rate up to 62.8%, and the prediction model by logistic regression analysis could classify those who had caused an accident at a rate up to 76.7%. In addition, as a result of the verification of model predictive power of the models showed an accuracy rate of 84.1%.

본 연구는 시내버스 운전자의 실제 운행기록 정보를 토대로 사고발생 가능성을 내포한 운전자를 판단할 수 있는 모형개발을 목적으로 하였다. 본 연구를 위하여 사고발생 운전자 및 사고 미발생 운전자의 실제 운행기록 정보에서 교통사고와 관련한 유의변수를 도출하는 한편, 판별분석(Discriminant Analysis) 및 로지스틱회귀분석(Logistic Regression Analysis)을 적용하여 개발된 분류모형에 대한 모형간 정확도를 비교하였다. 또한, 개발된 모형을 다른 운전자들의 운행기록자료에 적용하여 모형의 정확도를 검증하였다. 사고발생 가능성을 내포한 운전자 분류모형을 개발한 결과 감속도($X_{deceleration}$) 및 우측방향 가속도($Y_{right}$)가 동시에 작용할 때 이 변수가 사고발생 운전자 분류의 최적 요인변수로 도출되었으며, 판별분석에 의한 예측모형은 최대 62.8%, 로지스틱회귀분석에 의한 예측모형은 최대 76.7%의 비율로 사고 발생 운전자 분류가 가능한 것으로 나타났다. 또한, 모형 예측력에 대한 검증결과 84.1%의 적중률을 보이는 것으로 나타났다.

Keywords

References

  1. Bagadadi O. and Varhelyi A.(2011), "Jerky driving -An indicator of accident proneness," Accident Analysis and Prevention, vol. 43, pp. 1359-1363. https://doi.org/10.1016/j.aap.2011.02.009
  2. Cho J. H.(2008), "Development of a Real-time Safe Driving Management System," University of Kookmin, Ph. D. Dissertation.
  3. Cho J. H. and Lee W. S.(2007), "Development of a Safe Driving Management System," Transactions of Korea Society of Automotive Engineers, vol. 15, no. 1, pp.71-77.
  4. Hwang S. Ch.(2000), "A Study on the Causes of Traffic Casualties and Preventive Countermeasures," Dongguk University, Master's degree thesis.
  5. Lee H. S. and An B. J.(2006), "A Factor Analysis of Traffic Accidents Through Traffic Safety Diagnosis Results," Journal of the Korean Society of Safety, vol. 21, no. 2, pp.128-137.
  6. Oh J. S.(2011), "Discrimination for Reckless Drivers through Personality and Attitude Measurement : Developing a Psychological Test and Its Criteria for Driver Discrimination," Chungbuk National University, Ph. D. Dissertation.
  7. Oh J. T. and Lee S. Y.(2009), "A Study of the Weight value to Risky Driving Type," International Journal of Highway Engineering, vol. 11, no. 1, pp.105-115.
  8. Park J. H. and Lee S. Ch.(1997), "Analysis of Traffic Accident Proneness by Drivers' Variables," Korean Journal of Culture and Social Issues, vol. 3, no. 1, pp.143-157.
  9. af Wahlberg. AE(2004), "The stability of driver acceleration behavior, and a replication of its relation to bus accidents," Accident Analysis and Prevention, vol. 36, pp. 83-92. https://doi.org/10.1016/S0001-4575(02)00130-6
  10. Zegeer C., Huang H., Hummer J., Stutts J. and Rodgman E.(1993), "Characteristics and Solutions Related to Bus Transit Accidents," Federal Transit Administrationas.

Cited by

  1. 사업용차량 센서 자료를 이용한 도로안전정보 콘텐츠 개발 : 교통시뮬레이션 자료 분석을 중심으로 vol.19, pp.2, 2016, https://doi.org/10.12815/kits.2020.19.2.74
  2. Using vehicle data as a surrogate for highway accident data vol.174, pp.2, 2016, https://doi.org/10.1680/jmuen.20.00012