The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Severities of Rental Car Traffic Accidents using Naive Bayes Big Data Classifier

나이브 베이즈 빅데이터 분류기를 이용한 렌터카 교통사고 심각도 예측

  • Jeong, Harim (Dept. of Transportation Eng., Ajou University) ;
  • Kim, Honghoi (Ilmile Corp.) ;
  • Park, Sangmin (Dept. of Transportation Eng., Ajou University) ;
  • Han, Eum (Traffic Science Institute, Road Traffic Authority) ;
  • Kim, Kyung Hyun (Transportation Research Division, Korea Expressway Corporation Research Institute) ;
  • Yun, Ilsoo (Dept. of Transportation Eng., Ajou University)
  • 정하림 (아주대학교 건설교통공학과) ;
  • 김홍회 (일마일주식회사) ;
  • 박상민 (아주대학교 건설교통공학과) ;
  • 한음 (도로교통공단 교통과학연구원) ;
  • 김경현 (한국도로공사 도로교통연구원) ;
  • 윤일수 (아주대학교 교통시스템공학과)
  • Received : 2017.05.22
  • Accepted : 2017.07.20
  • Published : 2017.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Traffic accidents are caused by a combination of human factors, vehicle factors, and environmental factors. In the case of traffic accidents where rental cars are involved, the possibility and the severity of traffic accidents are expected to be different from those of other traffic accidents due to the unfamiliar environment of the driver. In this study, we developed a model to forecast the severity of rental car accidents by using Naive Bayes classifier for Busan, Gangneung, and Jeju city. In addition, we compared the prediction accuracy performance of two models where one model uses the variables of which statistical significance were verified in a prior study and another model uses the entire available variables. As a result of the comparison, it is shown that the prediction accuracy is higher when using the variables with statistical significance.

교통사고는 인적요인, 차량요인, 환경요인이 복합적으로 작용하여 발생한다. 이 중 렌터카 교통사고는 운전자의 평소 익숙하지 않은 환경 등으로 인해 교통사고 발생 가능성과 심각도가 다른 교통사고와는 다를 것으로 예상된다. 이에 본 연구에서는 국내 대표 관광도시인 부산광역시, 강릉시, 제주시를 대상으로 최근 빅데이터 분석에 사용되는 기계학습 기법중 하나인 나이브 베이즈 분류기를 이용하여 렌터카 교통사고의 심각도를 예측하는 모형을 개발하였다. 또한, 기존 연구에 유의성이 검증된 변수와 수집 가능한 모든 변수를 이용하는 두 가지 모형에 대하여 모형의 예측 정확도를 비교하였다. 비교 결과 통계적 기법을 통해 유의성이 검증된 변수를 사용할 경우 모형이 더 높은 예측 정확도를 보이는 것으로 나타났다.

Keywords

References

  1. Choi J. W., Kim S. H., Cho J. H. and Kim W. C.(2004), "A Study to predict the Traffic Accident Severity Level Applying Neural Network at the Signalized Intersections," Journal of Korean Society of Transportation, vol. 22, no. 3, pp.127-135.
  2. Choi S., Park J. H. and Oh C.(2011), "Factors Affecting Injury Severity in Pedestrian-Vehicle Crash by Novice Driver," Journal of Korean Society of Transportation, vol. 29, no. 4, pp.43-51.
  3. Kang J. H., Kim J. C., Lee J. H., Park S. S. and Jang D. S.(2016), "A Comparative Study on Patent Document Classification Algorithms," Proceedings of KIIS Spring Conference, vol 26, no. 1, pp.9-10.
  4. Kim J. S. and Shin Y. K.(2000), "An Automatic Document Classification with Bayesian Learning," Journal of the Korean Data & Information Science Society, vol. 11, no. 1, pp.19-30.
  5. Ko H. G., Yun I., Kim K. H., Song H. I. and Heo, T. Y.(2016), "A study on Analysis Severities of Rental Car Traffic Accidents : Case of Major Sightseeing Cities Including Busan, Gyeongju and Jeju Island," Journal of the Korean Data Analysis Society, vol. 18, no. 2, pp.755-769.
  6. Korea Road Traffic Authority(2016), Comparison of Traffic Accident of OECD Member States.
  7. Korea Transport Institution(2013), A Study on the Strategies for 'Vision Zero' Goal of Traffic Fatalities in Korea.
  8. Korean Transportation Safety Authority(2013), The twenties cause the half of the entire deadly traffic accidents involving rent cars, analysis of status of deadly rent car traffic accidents during recent 5 years.
  9. Won M. S., Lee G. R., Oh C. and Kang K. W.(2009), "A Study on the Application of Accident Severity Prediction Model," vol. 27, no. 4, pp.167-173.
  10. Park J. T., Lee S. B., Kim J. W. and Lee D. M.(2008), "Development of a Traffic Accident Prediction Model for Urban Signalized Intersections," Journal of Korean Society of Transportation, vol. 26, no. 4, pp.99-110.
  11. Park N. Y., Kim J. I. and Jung Y. G.(2013), "Breast Cancer Diagnosis using Naive Bayes Analysis Techniques," Journal of Service Research and Studies, vol. 3, no. 1, pp.87-93.
  12. Peter H.(2013), "Machine Learning in Action," JPub(Paju, Korea), pp.11-13.
  13. The R Foundation, https://www.r-project.org/, 2017.05.16.

Cited by

  1. Development and Comparison of Data Mining-based Prediction Models of Building Fire Probability vol.19, pp.6, 2017, https://doi.org/10.7472/jksii.2018.19.6.101