DOI QR코드

DOI QR Code

Development of a Model for Calculating the Negligence Ratio Using Traffic Accident Information

교통사고 정보를 이용한 과실비율 산정 모델 개발

  • Eum, Han (Dept. of Transportation Operation, Korea Road Traffic Authority) ;
  • Giok, Park (Korea Automobile Testing & Research Institute, Korea Transportation Safety Authority) ;
  • Heejin, Kang (Korea Automobile Testing & Research Institute, Korea Transportation Safety Authority) ;
  • Yoseph, Lee (Dept. of Transportation Eng., Univ. of Ajou) ;
  • Ilsoo, Yun (Dept. of Transportation Eng., Univ. of Ajou)
  • 한음 (도로교통공단 교통운영연구처) ;
  • 박기옥 (한국교통안전공단 자동차안전연구원) ;
  • 강희진 (한국교통안전공단 자동차안전연구원) ;
  • 이요셉 (아주대학교 교통공학과) ;
  • 윤일수 (아주대학교 교통시스템공학과)
  • Received : 2022.10.10
  • Accepted : 2022.11.07
  • Published : 2022.12.31

Abstract

Traffic accidents occur in Korea are calculated with the 「Automobile Accident Negligence Ratio Certification Standard」 prepared by the 'General Insurance Association of Korea' and the insurance company's agreement or judgment is made. However, disputes are frequently occurring in calculating the negligence ratio. Therefore, it is thought that a more effective response would be possible if accident type according to the standard could be quickly identified using traffic accident information prepared by police. Therefore, this study aims to develop a model that learns the accident information prepared by the police and classifies it to match the accident type in the standard. In particular, through data mining, keywords necessary to classify the accident types of the standard were extracted from the accident data of the police. Then, models were developed to derive the types of accidents by learning the extracted keywords through decision trees and random forest models.

국내에서 발생하는 교통사고는 손해보험협회에서 작성한 「자동차사고 과실비율 인정기준」에 따라 과실비율을 산정하며, 이를 통해 보험사의 합의나 판결이 내려진다. 하지만, 과실비율 산정에 있어 분쟁이 빈번하게 일어나고 있다. 따라서, 교통사고 발생 시 경찰공무원에 의해 작성되는 교통사고 정보를 이용하여 「자동차사고 과실비율 인정기준」 상의 교통사고 유형을 신속하게 확인할 수 있다면, 보다 효과적인 대응이 가능할 것으로 사료된다. 이에 본 연구에서는 경찰에 의해 작성된 교통사고 정보를 학습시켜 「자동차사고 과실비율 인정기준」 에서 제시하는 교통사고 유형으로 분류하는 모델을 개발하고자 한다. 특히, 데이터마이닝을 통해 경찰청 교통사고 데이터에서 「자동차사고 과실비율 인정기준」 의 교통사고 유형으로 분류하는 데 필요한 핵심어들을 추출하였다. 그리고, 키워드를 의사결정나무 및 랜덤 포레스트 모델을 통해 학습시켜 교통사고 유형을 도출하는 모델을 개발하였다.

Keywords

Acknowledgement

본 연구는 국토교통부/국토교통과학기술진흥원의 지원으로 수행되었음(21AMDP-C162419-01, 자율주행기술개발혁신사업). 본 논문은 2022년 한국ITS학회 춘계학술대회에 게재되었던 논문을 수정·보완하여 작성하였습니다.

References

  1. Brreiman, L.(2001), "Random forests", Machine Learning, vol. 45, pp.5-32. https://doi.org/10.1023/A:1010933404324
  2. General Insurance Association of Korea(KNIA), https://vwserver.kif.re.kr/flexer/viewer.jsp?dir=km&cno=304116&fk=2022004700RF&ftype=hwp, 2022.04.20. 
  3. Heo, T., Kim, D. and Hwang, S.(2021), "Identification of Celtis species using random forest with infrared spectroscopy and analysis of spectral feature importance", Journal of the Korean Data & Information Science Society, vol. 32, no. 6, pp.1183-1194.  https://doi.org/10.7465/jkdi.2021.32.6.1183
  4. Jang, C.(2009), "A Study on Consumption Revitalization Strategies of Fair Trade Commodity Using Decision Tree Model", Korea Journal of Food Marketing Economics, vol. 26, no. 1, pp.51-71. 
  5. Jeong, H. R., Park, S. M., Jun, Y. J., Choi, J. W., Park, K. H. and Yun, I. S.(2016), "Reclassification of Traffic Crashes Using Traffic Crash Report Data and Keyword Analysis," 13th International Conference on Probabilistic Safety Assessment and Management. 
  6. Joen, S.(2019), A study on the determination of fault rates by adjusters in automobile accidents, Doctoral Dissertation, Pukyong National University. 
  7. Jung, S.(2012), "The definition of negligence in the caseson traffic accidents", Korean Lawyers Association Journal, vol. 61, no. 9, pp.174-207.  https://doi.org/10.17007/klaj.2012.61.9.004
  8. Kang, K.(2019), "Decision Tree Techniques with Feature Reduction for Network Anomaly Detection", Journal of The Korea Institute of Information Security & Cryptology, vol. 29, no. 4, pp.795-805.  https://doi.org/10.13089/JKIISC.2019.29.4.795
  9. Kang, S., Park, Y., Jo, S. and Yoon, S.(2013), "A Study on Proper Conducting Volume of Traffic Accident Investigator", The Journal of Police Science, vol. 13, no. 3, pp.143-162.  https://doi.org/10.22816/POLSCI.2013.13.3.006
  10. Kim, E.(2018), "A Study on Liability & Compensation Pursuant to Fault Ratio and the Rule of Risk Diversification in Automobile Insurance", Ilkam Law Review, vol. 39, pp.25-51.  https://doi.org/10.35148/ilsilr.2018..39.25
  11. Kim, S. and Ahn, H.(2016), "Application of Random Forests to Corporate Credit Rating Prediction", Journal of Industrial Innovation, vol. 32, no. 1, pp.187-211. 
  12. Korea Duck Association(2008), "Compensation for Damages Cused by a Farmer's Traffic Accident", Monthly Duck's Village, no. 57, pp.58-62. 
  13. Lee, G. and Lee, H.(2003), "A Study on the Combined Decision Tree(C4.5) and Neural Network Algorithm for Classification of Mobile Telecommunication Customer", Journal of Intelligence and Information Systems, vol. 9, no. 1, pp.139-155. 
  14. Lee, S. and Kim, H.(2009), "Keword Extraction from News Corpus using Modified TF-IDF", Journal of Society for e-Business Studies, vol. 14, no. 4, pp.59-74. 
  15. Park, S., So, J., Ko, H., Jung, H. and Yun, I.(2019), "Development of Safety Evaluation Scenarios for Autonomous Vehicle Tests Using 5-Layer Format(Case of the Community Road)", Journal of Korea Institute of Intelligent Transport Systems, vol. 18, no. 2, pp.114-128.  https://doi.org/10.12815/kits.2019.18.2.114
  16. Powers, D. M.(2011), "Evaluation: From Precision, Recall and F-measure to ROC, Informedness, Markedness & Correlation", Journal of Machine Learning Technologies, vol. 2, no. 1, pp.37-63. 
  17. Singh, S. and Gupta, P.(2014), "Comparative study ID3, cart and C4. 5 decision tree algorithm: A survey", International Journal of Advanced Information Science and Technology(IJAIST), vol. 27, no. 27, pp.97-103. 
  18. Yoo, J.(2015), "Random forests, an alternative data mining technique to decision tree", Journal of Educational Evaluation, vol. 28, no. 2, pp.427-448.