DOI QR코드

DOI QR Code

Development of Optimum Traffic Safety Evaluation Model Using the Back-Propagation Algorithm

역전파 알고리즘을 이용한 최적의 교통안전 평가 모형개발

  • 김중효 (도로교통공단 교통과학연구원) ;
  • 권성대 (전남대학교 공업기술연구소) ;
  • 홍정표 (한국도로공사 진안지사) ;
  • 하태준 (전남대학교 토목공학과)
  • Received : 2015.02.28
  • Accepted : 2015.04.20
  • Published : 2015.06.01

Abstract

The need to remove the cause of traffic accidents by improving the engineering system for a vehicle and the road in order to minimize the accident hazard. This is likely to cause traffic accident continue to take a large and significant social cost and time to improve the reliability and efficiency of this generally poor road, thereby generating a lot of damage to the national traffic accident caused by improper environmental factors. In order to minimize damage from traffic accidents, the cause of accidents must be eliminated through technological improvements of vehicles and road systems. Generally, it is highly probable that traffic accident occurs more often on roads that lack safety measures, and can only be improved with tremendous time and costs. In particular, traffic accidents at intersections are on the rise due to inappropriate environmental factors, and are causing great losses for the nation as a whole. This study aims to present safety countermeasures against the cause of accidents by developing an intersection Traffic safety evaluation model. It will also diagnose vulnerable traffic points through BPA (Back -propagation algorithm) among artificial neural networks recently investigated in the area of artificial intelligence. Furthermore, it aims to pursue a more efficient traffic safety improvement project in terms of operating signalized intersections and establishing traffic safety policies. As a result of conducting this study, the mean square error approximate between the predicted values and actual measured values of traffic accidents derived from the BPA is estimated to be 3.89. It appeared that the BPA appeared to have excellent traffic safety evaluating abilities compared to the multiple regression model. In other words, The BPA can be effectively utilized in diagnosing and practical establishing transportation policy in the safety of actual signalized intersections.

교통사고 피해를 최소화하기 위해서는 차량과 도로 체계에 대한 공학적인 개선을 통하여 교통사고 원인을 제거해야 한다. 일반적으로 안정성과 효율성이 부족한 도로는 교통사고가 지속적으로 발생할 가능성이 크고 이를 개선하는데 막대한 사회적 비용과 시간이 소요되며, 부적절한 환경 요인으로 발생한 교통사고는 국가적으로 큰 피해를 발생시키게 된다. 따라서 본 연구는 최근 인공지능 분야 중 활발히 연구 중인 역전파 알고리즘(Back-Propagation Algorithm : BPA)을 이용하여 신호교차로를 대상으로 최적의 교통안전 평가기법을 제시하고자 하였다. 본 연구는 광주광역시내 교통혼잡과 교통사고가 빈번하게 발생하고 있는 신호교차로 지점을 대상으로, BPA를 이용하여 보다 신뢰성 높은 교통안전 평가 모형을 개발하고자 다음과 같은 일련의 방법으로 연구를 수행하였다. 첫째, 신호교차로 교통사고와 교통상충간의 순위상관분석을 실시하여 교통사고 순위와 교통상충 순위가 통계적으로 유의함을 확인하였다. 이는 교통상충이 신호교차로 교통안전 평가 변수로 사용될 수 있음에 따라 설명변수로 입력되고 교통사고가 종속변수인 선형회귀모형을 개발하는데 이용하였다. 둘째, 신호교차로의 교통량과 진입 진출 차로수 차이 등을 교통사고의 설명변수로 간주하여 다중회귀분석을 통해 교통사고 예측모형을 개발하였다. 셋째, 교통량과 도로 기하구조 요소를 모형의 설명변수로 설정하고 교통상충을 종속변수로 하여 BPA를 이용한 최적의 교통안전 평가 모형을 개발하였다. 마지막으로, 교통사고 실측값, 다중회귀모형, BPA에 의한 교통사고 예측값을 평균제곱근오차 방법으로 모형의 적합도 비교 분석을 하였다. 본 연구의 결과, BPA에 의해 도출된 교통사고 예측값과 교통사고 실측값 사이의 평균제곱오차는 3.89로 계산되어 BPA가 다중회귀 모형보다 상대적으로 교통안전 평가능력이 우수한 것으로 나타나 실제 신호교차로 교통안전도를 평가하는데 효과적으로 활용될 수 있을 것으로 판단되고 추후, 교통안전정책 수립시 실질적인 도움이 될 것으로 기대된다.

Keywords

References

  1. Adler, B. and Alfaro, L. (2007). "A content-driven reputation system for Wikipedia." Proc. of the 16th international conference on World wide web, NewYork, N.Y., pp. 261-270.
  2. Agichtein, E. (2005). "Web information extraction and user modeling: Towards Closing the Gap." IEEE Data Engineering Bulletin, Vol. 28, No. 4.
  3. Agrawal, S., Chaudhuri, S. and Das, G. (2002). "DB explorer : A System for Keyword Search over Relational Databases." In Proc. of ICDE-02.
  4. Bang, K. L., Lindberg, G. and Harahap, G. (1997). "Development of guidelines based on life-cycle cost to replace level-of-service conception capacity analysis." Transportation Research Record : Journal of the Transportation Research Board, No. 1572, pp. 10-17.
  5. Chol, J. (1998). "Development of a traffic safety index for urban arterials." Journal of Korean Society of Transportation, Vol. 16, No. 3, pp. 47-56.
  6. Greibe, P. (2003). "Accident prediction models for uban roads." Accident Analysis Prevention, Vol. 35, No. 2, pp. 273-285. https://doi.org/10.1016/S0001-4575(02)00005-2
  7. IYM, Y. T. (2011). "Development of traffic accident frequency prediction model in urban signalized intersections with fuzzy reasoning and neural network theories." Journal of Korean Society of Road Engineers, Vol. 13, No. 1, pp. 69-77.
  8. Jacobson, G., Booch, and Rumbaugh, J. (1999). The unified software development process, Addison-Wesley Publishing Company.
  9. Jang, J., Lee, Y., Kim, H. and Jang, M. (2000). "The method of deciding design level of service with optimal user cost." Journal of Korean Society of Transportation, Vol. 18, No. 2, pp. 17-26.
  10. Kang, Y. K. (2011). "Development of traffic accident frequency prediction model in urban signalized intersections with fuzzy reasoning and neural network theories." Journal of Korean Society of Road Engineers, Vol. 13, No. 1, pp. 69-77.
  11. Kim, E. C. (2008). "Development of traffic accident frequency model for evaluating safety at rural signalized intersections." Journal of Korean Society of Road Engineers, Vol. 10, No. 4, pp. 53-63.
  12. Kim, K. W. (2012). "Building a traffic accident frequency prediction model at unsignalized intersections in urban areas by using adaptive neuro-fuzzy inference system." Journal of Korean Society of Civil Engineers, Vol. 32, No. 2D, pp. 137-145. https://doi.org/10.12652/KSCE.2012.32.2D.137
  13. Kong, S. H. (2003). "Traffic accident frequency model using the genetic-supervised artificial neural network." Journal of Korean Society of Civil Engineers, Vol. 23, No. 4, pp. 479-487.
  14. Lee, C. N. (1998). "Identification of variables influencing traffic accidents on urban arterials using neural network." Journal of Korean Society of Civil Engineers, Vol. 18, No. 3, pp. 803-810.
  15. Lee, J. M. (2008). "Developing the traffic accident prediction model using classification and regression tree analysis." Journal of Korean Society of Civil Engineers, Vol. 10, No. 4, pp. 31-39.
  16. Lee, S. B. (2003). "Development of a traffic accident predication model by level of roads and traffic characteristics." Journal of Korean Society of Civil Engineers, Vol. 23, No. 4D, pp. 495-504.
  17. Nam, G. H. (2001). "Development and application of traffic accident forecasting model for signalized intersections (Four-Legged Signalized Intersections in Kwang-Ju)." Journal of Korean Society of Transportation, Vol. 19, No. 6. pp. 207-218.
  18. Shim, K. B. (1994). "Analysis of traffic accident by the relation parameters in city arterial roads." Journal of Traffic Safety Research, Vol. 13, pp. 125-136.
  19. Son, E. Y. (1992). A study of estimating traffic congestion costs, The Korea Transport Institute (in Korean).
  20. Sung, N. M. (2008). "Development of severity model for rural unsignalized intersection crashes." Journal of Korean Society of Road Engineers, Vol. 10, No. 3, pp. 47-56.
  21. Trujillo, J., Palomar, M., Gomez, J. and Song, Y. (2001). "Designing data warehouses with conceptual models." Computer IEEE, pp. 66-75.