DOI QR코드

DOI QR Code

A Study for Development of Expressway Traffic Accident Prediction Model Using Deep Learning

딥 러닝을 이용한 고속도로 교통사고 건수 예측모형 개발에 관한 연구

  • 류종득 (한국도로공사 수도권건설사업단) ;
  • 박상민 (아주대학교 건설교통공학과) ;
  • 박성호 (아주대학교 건설교통공학과) ;
  • 권철우 (아주대학교 건설교통공학과) ;
  • 윤일수 (아주대학교 교통시스템공학과)
  • Received : 2018.06.10
  • Accepted : 2018.07.08
  • Published : 2018.08.31

Abstract

In recent years, it has become technically easier to explain factors related with traffic accidents in the Big Data era. Therefore, it is necessary to apply the latest analysis techniques to analyze the traffic accident data and to seek for new findings. The purpose of this study is to compare the predictive performance of the negative binomial regression model and the deep learning method developed in this study to predict the frequency of traffic accidents in expressways. As a result, the MOEs of the deep learning model are somewhat superior to those of the negative binomial regression model in terms of prediction performance. However, using a deep learning model could increase the predictive reliability. However, it is easy to add other independent variables when using deep learning, and it can be expected to increase the predictive reliability even if the model structure is changed.

최근 빅데이터 시대의 도래와 함께 교통사고와 관련된 요인을 설명하기 용이해졌다. 이에따라 최신 분석 기법을 적용하여 교통사고 자료를 분석하고 시사점을 도출할 필요가 있다. 본 연구의 목적은 고속도로 교통사고 자료를 이용하여 고속도로의 주요 분석 단위인 콘존의 교통사고 건수를 예측하기 위하여 음이항 회귀모형과 딥 러닝을 이용한 기법을 적용하고 예측 성능을 비교하였다. 예측 성능 비교 결과, 딥 러닝 모형의 MOE들이 음이항 회귀모형에 비해 다소 우수한 것으로 나타났으나, MAD 기준으로 차이는 미미한 것으로 나타났다. 하지만 딥 러닝을 이용할 경우 다른 독립변수들을 추가하는 것이 용이하고, 모형의 구조 등을 변경할 경우 예측 신뢰도를 더욱 증가시킬 수 있을 것으로 판단된다.

Keywords

References

  1. Huang H., Zeng Q., Pei X., Wong S. C. and Xu P.(2016), "Predicting crash frequency using an optimised radial basis function neural network model," Transportmetrica A: Transport Science, vol. 12, no 4, pp.330-345. https://doi.org/10.1080/23249935.2015.1136008
  2. Jung J.(2014), Poisson regression and negative binomial regression fit for traffic accidents, Master thesis, Korea University.
  3. Korea Expressway Corporation(2014), Highway Safety Performance Accident Correction Factor Development Casebook.
  4. Lu J., Haleem K., Alluri P. and Gan A.(2013), "Full versus simple safety performance functions: a comparison based on urban four-lane freeway interchange influence areas in Florida," Transportation Research Board Annual Meeting.
  5. National Police Agency(2017), Traffic Accident Statistics in 2016.
  6. Oh Y. T. and Kang D. S.(2017), Advanced Traffic Safety Engineering.
  7. Pan G., Fu L. and Thakali L.(2017), "Development of a global road safety performance function using deep neural networks," International Journal of Transportation Science and Technology, vol. 6, no. 3, pp.159-173. https://doi.org/10.1016/j.ijtst.2017.07.004
  8. Ryu J.(2018), Development of expressway traffic accident prediction model using deep learning, Doctoral thesis, Ajou University.
  9. Seo I. K., Kang D. Y., Park J. J. and Park S. H.(2015), "Development of safety performance function based on expressway alignment homogeneous section," Journal of the Korean Society of Civil Engineers, vol. 35, no. 2, pp.397-405. https://doi.org/10.12652/Ksce.2015.35.2.0397

Cited by

  1. 딥러닝 기반의 보행자 탐지 및 경보 시스템 연구 vol.18, pp.4, 2019, https://doi.org/10.12815/kits.2019.18.4.58