교통사고 데이터의 패턴 분석과 Hybrid Model을 이용한 피해자 상해 심각도 예측

Pattern Analysis of Traffic Accident data and Prediction of Victim Injury Severity Using Hybrid Model

  • 주영지 (조선대학교 소프트웨어융합공학과) ;
  • 홍택은 (조선대학교 소프트웨어융합공학과) ;
  • 신주현 (조선대학교 제어계측로봇공학과)
  • 투고 : 2016.12.15
  • 심사 : 2016.12.26
  • 발행 : 2016.12.31

초록

우리나라의 경제 성장과 도로 환경의 변화를 통해 국내 자동차 시장이 성장하였으나, 이로 인해 교통사고율 또한 증가하였고, 인명 피해가 심각한 수준이다. 이에 따라, 정부에서는 교통사고 데이터를 개방하고 문제를 해결하기 위한 정책을 수립 및 추진 중이다. 본 논문에서는 교통사고 데이터를 이용하여 클래스의 불균형을 해소하고, Hybrid Model 구축을 통한 교통사고 예측을 위해 원본 교통사고 데이터와 Sampling을 수행한 데이터를 학습 데이터로 사용한다. 두 학습데이터에 연관규칙 학습기법인 FP-Growth 알고리즘을 이용하여 교통사고 상해 심각도와 연관된 패턴을 학습한다. 두 학습 데이터의 연관 패턴을 분석을 통해 같은 연관된 패턴을 추출하고 의사결정트리와 다항 로지스틱 회귀분석기법에 연관된 속성에 가중치를 부여하여 융합형 Hybrid Model을 구축하고 교통사고 피해자 상해 심각도를 예측하는 방법에 대해 제안한다.

Although Korea's economic and domestic automobile market through the change of road environment are growth, the traffic accident rate has also increased, and the casualties is at a serious level. For this reason, the government is establishing and promoting policies to open traffic accident data and solve problems. In this paper, describe the method of predicting traffic accidents by eliminating the class imbalance using the traffic accident data and constructing the Hybrid Model. Using the original traffic accident data and the sampled data as learning data which use FP-Growth algorithm it learn patterns associated with traffic accident injury severity. Accordingly, In this paper purpose a method for predicting the severity of a victim of a traffic accident by analyzing the association patterns of two learning data, we can extract the same related patterns, when a decision tree and multinomial logistic regression analysis are performed, a hybrid model is constructed by assigning weights to related attributes.

키워드

참고문헌

  1. Ministry of Land, Infrastructure and Transport
  2. TAAS Traffic Accident Analysis System
  3. C.K. Lee, "A Study of Big Data Information Systems Building and Cases," Journal of the KISM Smart Media, Vol.4, No.3, pp. 56-61, 2015.
  4. S.S. Han and B.H. Park, "Comparative Analysis of Traffic of Cheongju," Korea Planning Association, Vol. 46, No. 2, pp. 183-192, 2011.
  5. S.Y. Sohn and S.H. Lee, "Data Fusion, Ensemble and Clustering for the Severity Classification of Read Traffic Accident in Korea," Safety Science, Vol. 41, No. 1, pp. 1-14, 2013. 5. https://doi.org/10.1016/S0925-7535(01)00032-7
  6. Chang, M., A. Abraham and M. Paprzycki, "Traffic Accident Analysis Using Machine Learning Paradigms," Informatica, Vol. 29, pp. 89-98, 2005.
  7. J.S. Lee and K. Huh, "Injury Severity Prediction of Traffic Accident using Data Mining," General Autumn Conference of Korea Intelligent Information System Society, pp. 199-206, 2011.
  8. S.E. Hong, G.Y. Lee and H.J Kim, "A Study on Traffic Accident Injury Severity Prediction Model Based on Public Data," Jornal of KIIT, Vol. 13, No. 5, pp. 109-118, 2015.
  9. J.S. Lee and E.J. Lee, "Analysis of Traffic Accident using Decision Tree Ensemble Model," General Autumn Conference of Korea Intelligent Information System Society, Vol. 11, pp. 211-218, 2009.
  10. E.J. Lee, "Analysis of Traffic Accidents using Data Mining Ensemble Models," Master's Thesis, Ajou University, 2010.
  11. J.S. Lee, J.G. Kwon, "A Hybrid SVM Classifier for Imbalanced Data Sets," Journal of Intelligent Information Systems, No. 19, Vol. 2, pp. 125-140, 2013.
  12. Jason Bell, "machine Learning: Hands-On for Developers and Technical Professionals," John Wiley & Sons, pp. 1-408, 2014
  13. J.S. Lee and J.C. Lee, "Customer Chum Prediction by Hybrid Model," Advanced Data Mining and Applications, Vol. 4093, pp. 959-966, 2006.