Journal of Korean Society of Transportation (대한교통학회지)

Korean Society of Transportation (대한교통학회)
권호 표지
DOI QR코드

DOI QR Code

A Comparative Study On Accident Prediction Model Using Nonlinear Regression And Artificial Neural Network, Structural Equation for Rural 4-Legged Intersection

비선형 회귀분석, 인공신경망, 구조방정식을 이용한 지방부 4지 신호교차로 교통사고 예측모형 성능 비교 연구

  • Oh, Ju Taek (Department of Urban Engineering, Korea National University of Transportation) ;
  • Yun, Ilsoo (Department of Transportation Systems Engineering, Ajou University) ;
  • Hwang, Jeong Won (Department of Urban Engineering, Korea National University of Transportation) ;
  • Han, Eum (Department of Transportation Systems Engineering, Ajou University)
  • 오주택 (한국교통대학교 도시공학과) ;
  • 윤일수 (아주대학교 교통시스템공학과) ;
  • 황정원 (한국교통대학교 도시공학과) ;
  • 한음 (아주대학교 교통시스템공학과)
  • Received : 2013.11.05
  • Accepted : 2014.03.03
  • Published : 2014.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

For the evaluation of roadway safety, diverse methods, including before-after studies, simple comparison using historic traffic accident data, methods based on experts' opinion or literature, have been applied. Especially, many research efforts have developed traffic accident prediction models in order to identify critical elements causing accidents and evaluate the level of safety. A traffic accident prediction model must secure predictability and transferability. By acquiring the predictability, the model can increase the accuracy in predicting the frequency of accidents qualitatively and quantitatively. By guaranteeing the transferability, the model can be used for other locations with acceptable accuracy. To this end, traffic accident prediction models using non-linear regression, artificial neural network, and structural equation were developed in this study. The predictability and transferability of three models were compared using a model development data set collected from 90 signalized intersections and a model validation data set from other 33 signalized intersections based on mean absolute deviation and mean squared prediction error. As a result of the comparison using the model development data set, the artificial neural network showed the highest predictability. However, the non-linear regression model was found out to be most appropriate in the comparison using the model validation data set. Conclusively, the artificial neural network has a strong ability in representing the relationship between the frequency of traffic accidents and traffic and road design elements. However, the predictability of the artificial neural network significantly decreased when the artificial neural network was applied to a new data which was not used in the model developing.

도로의 안전성을 평가하기 위한 방법으로서 교통사고 자료를 이용하는 방법, 사전-사후평가를 통한 방법 또는 전문가 의견이나 기존 문헌을 통한 방법 등 다양한 방법들이 존재한다. 특히, 교차로 교통 안전성을 평가하는 경우 많은 연구들이 교통사고예측모형 개발을 통하여 교통사고와 관련한 원인과 안전성을 평가하고 있다. 교통사고예측모형 개발에 있어서 모형의 예측력과 전용성을 확보하는 것이 중요하다. 즉, 예측력을 확보함으로써 교통사고 건수나 교통 안전성 판단의 지표를 예측하는데 오차를 줄일 수 있고, 전용성을 확보함으로써 개발된 모형이 다른 지점이나 구간에 적용하더라도 문제없이 적용될 수 있는 대표성을 가질 수 있다. 따라서 본 연구에서는 교통사고예측모형 개발에 주로 사용되는 회귀모형과 인공신경망, 구조방정식을 이용하여 교통사고예측모형을 각각 개발하였으며, 개발될 모형의 예측력과 전용성을 평균절대오차와 평균제곱예측오차를 기준으로 확인하였다. 90개소 신호교차로의 모형개발자료를 이용하여 세 가지 방법으로 교통사고예측모형을 개발 후 개발데이터를 통해 예측력을 비교한 결과 인공신경망이 가장 높은 예측력을 보였다. 또한 모형의 전용성 검증을 위하여 별도로 수집한 33개소 신호교차로의 모형검증자료를 이용하여 개발된 모형을 검증한 결과 비선형 회귀모형이 가장 적합한 것으로 나타났다. 모형개발 과정에서 가장 높은 예측력을 보인 인공신경망의 경우 다른 대상지에서 수집된 모형검증 자료를 적용하였을 때 예측력에 큰 변화를 보여 전용성이 떨어진 것으로 분석되었다.

Keywords

References

  1. Bauer K. M., Harwood D. W. (1997), Statistical Models of At-grade Intersection Accidents, Federal Highway Administration, FHWA-RD-96-125.
  2. Choi J. W., Kim S. H., Cho J. H., Kim W. C. (2004), A Study to Predict the Traffic Accident Severity Level Applying Neural Network at the Signalized Intersections, J. Korean Soc. Transp., 22(3), Korean Society of Transportation, 127-135.
  3. Ha O. G. (2005), Development of Accident Prediction Models and Accident Injury Severity for Rural Signalized Intersections, Hanyang University graduate school, A master Dissertation.
  4. Ha T. J., Kang J. K., Park J. J. (2001), Development and Application of Traffic Accident Forecasting Model for Signalized Intersections (Four-Legged Signalized Intersections in Kwang-Ju), J. Korean Soc. Transp., 19(6), Korean Society of Transportation, 207-218.
  5. Harwood D. W., Bauer K. M., Potts I. B., Torbic D. J., Richard K. R., Kohlman Rabbani E. R. et al. (2002), Safety Effectiveness of intersection Left and Right-Turn Lanes, Federal Highway Administration, FHWA-RD-02-089.
  6. Hong J. Y., Doh C. W. (2002), Development of a Traffic Accident Prediction Model and Determination of the Risk Level at Signalized Intersection, J. Korean Soc. Transp., 20(7), Korean Society of Transportation, 155-166.
  7. Hong S. H. (2000), The Criteria for Selecting Appropriate Fit Indices in Structural Equation Modeling and Their Rationales, The Korean Journal of Clinical Psychological, 19(1), 161-177.
  8. Jo J. I. (2008), Analysis of factors affecting pedestrian injury severity, Hanyang University graduate school, A master Dissertation.
  9. Kang Y. K., Kim J. W., Lee S. I., Lee S. B. (2011), Development of Traffic Accident Frequency Prediction Model in Urban Signalized Intersections with Fuzzy Reasoning and Neural Network Theories, J. Korea Soc. Road Eng., 13(1), 69-77. https://doi.org/10.7855/IJHE.2011.13.1.069
  10. Kim D. H., Lee D. M., Sung N. M. (2010), A Development of Traffic Crash Frequency Prediction Models for Rural 3-Lagged Intersections, Journal of transport Research, 17(1), 37-48.
  11. Kim E. C., Lee D. M., Kim D. H. (2008), Development of Traffic Accident Frequency Model for Evaluating Safety at Rural Signalized Intersections, J. Korea Soc. Road Eng., 10(4), 53-63.
  12. Kim K. S. (2010), AMOS 18.0, Hannarae Academy, Korea.
  13. Kim S. R., Bae Y. K., Chung J. H., Kim H. J. (2011), Factor Analysis of Accident Types on Urban Street using Structural Equation Modeling(SEM), J. Korean Soc. Transp., 29(3), Korean Society of Transportation, 93-101.
  14. Kim W. C., Lee S. B., Namgung M., Hirofumi I. (2001), Constructing Method of Traffic Accidents Prediction Model for Safety Evaluation at Intersections, KSCE Journal of Civil Engineering, 21(4-D), korean society of civil engineers, 427-435.
  15. Lee H. S., Lim J. H. (2011), SPSS 18.0 Manual, Korea.
  16. Lee J. K. (2009), A Study on Prediction of the Early-Age Strength of Concrete using Artificial Neural Network Theory, Joongbu University graduate school, A master Dissertation.
  17. Lee J. P. (2001), Application of Artificial Neural Network to Predict Speed on Two-lane Rural Highway, Hanyang University graduate school, A master Dissertation.
  18. Lee J. Y., Chung J. H., Son B. S. (2008), Analysis of Traffic Accident Severity for Korean Highway Using Structural Equations Model, J. Korean Soc. Transp., 26(2), Korean Society of Transportation, 17-24.
  19. Lee S. W. (2002), The Study on the Selecting Optimal Artificial Neural Networks Model Prior to Forecasting Stock. Inje University graduate school, A master Dissertation.
  20. McCoy P. T., Malone M. S. (1989), Safety Effects of Left-Turn Lanes on Urban Four-Lane Roadways, Transportation Research Board, TRB, 1239, 17-22.
  21. Neter J., Kutner M., Wasserman W., Nachtsheim C. (1996), Applied Linear Statistical Models-four edition, A Division of the McGraw-Hill Companies, USA.
  22. Oh C., Kang Y. S., Kim B. I. (2006), Development of Pedestrian Fatality Model using Bayesian-Based Neural Network, J. Korean Soc. Transp., 24(2), Korean Society of Transportation, 139-145.
  23. Oh I. S., Kim S. S., Shin C. H. (2007), Development of Traffic Accident Forecasting Model for Signalized Intersections -Focusing National Highway in Kyonggi Province-, The 57th Conference of Korean Society of Transportation, Korean Society of Transportation, 315-322.
  24. Oh J. T., Kim D. H., Lee D. M. (2012), Development of the Expected Safety Performance Models for Rural Highway Segments, J. Korea Soc. Road Eng., 14(2), 131-143. https://doi.org/10.7855/IJHE.2012.14.2.131
  25. Park B. H., Han S. W., Kim T. Y., Kim W. H. (2008), Traffic Accident Models of Cheongju Four-Legged Signalized Intersections by Accident Type, J. Korean Soc. Transp., 26(5), Korean Society of Transportation, 153-162.
  26. Park J. T., Kim J. W., Lee S. B., Lee D. M. (2008), Development of a Traffic Accident Prediction Model for Urban Signalized Intersections, J. Korean Soc. Transp., 26(4), Korean Society of Transportation, 99-110.
  27. Poch M., Mannering F. L. (1996), Nagative Binomial Analysis of Intersection Accident Frequencies, Journal of Transportation Engineering, ASCE, 122(2), 105-113. https://doi.org/10.1061/(ASCE)0733-947X(1996)122:2(105)
  28. Shim J. H., Cho C. H., Lee S. H. (2007), The Industrial Land Price Appraisal based on Artificial Neural Network, Journal of korean Planner Association, 42(5), Korean Planner Association, 223-232.
  29. Vogt A. (1999), Crash Models for Rural Intersection: Four-Lane by Two-Lane Stop Controlled and Two- Lane Signalized, Federal Highway Administration, FHWA-RD-99-128.

Cited by

  1. Design and Application of Traffic Safety Technology in Chungcheong non-urban Region vol.17, pp.4, 2016, https://doi.org/10.5762/KAIS.2016.17.4.264
  2. A Novel Data Prediction Model using Data Weights and Neural Network based on R for Meaning Analysis between Data vol.18, pp.4, 2015, https://doi.org/10.9717/kmms.2015.18.4.524
  3. Traffic Safety Technology Proposal for Chungcheong Region vol.16, pp.2, 2015, https://doi.org/10.5762/KAIS.2015.16.2.1524
  4. Development of Traffic Accident Models at Rural Signalized Intersections by Day and Night vol.17, pp.3, 2015, https://doi.org/10.7855/IJHE.2015.17.3.107
  5. 대중교통카드를 이용한 환승요인분석 vol.16, pp.1, 2014, https://doi.org/10.12815/kits.2017.16.1.50
  6. Towards a cognitive warning system for safer hybrid traffic vol.11, pp.4, 2014, https://doi.org/10.3233/idt-170305
  7. ICT기반 횡단보도용 교통안전 통합시설물 개발 vol.18, pp.12, 2014, https://doi.org/10.5762/kais.2017.18.12.93