KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Safety Grade of Bridges Using the Classification Models of Decision Tree and Random Forest

의사결정나무 및 랜덤포레스트 분류 모델을 이용한 교량 안전등급 예측

  • 홍지수 (아주대학교 건설시스템공학과) ;
  • 전세진 (아주대학교 건설시스템공학과)
  • Received : 2023.04.19
  • Accepted : 2023.05.10
  • Published : 2023.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

The number of deteriorated bridges with a service period of more than 30 years has been rapidly increasing in Korea. Accordingly, the importance of advanced maintenance technologies through the predictions of age-induced deterioration degree, condition, and performance of bridges is more and more noticed. The prediction method of the safety grade of bridges was proposed in this study using the classification models of the Decision Tree and the Random Forest based on machine learning. As a result of analyzing these models for the 8,850 bridges located in national roads with various evaluation indexes such as confusion matrix, balanced accuracy, recall, ROC curve, and AUC, the Random Forest largely showed better predictive performance than that of the Decision Tree. In particular, random under-sampling in the Random Forest showed higher predictive performance than that of other sampling techniques for the C and D grade bridges, with the recall of 83.4%, which need more attention to maintenance because of the significant deterioration degree. The proposed model can be usefully applied to rapidly identify the safety grade and to establish an efficient and economical maintenance plan of bridges that have not recently been inspected.

국내에서 공용연수 30년 이상인 노후 교량의 수가 급증하고 있다. 이에 따라 교량 노후도, 상태 및 성능 예측을 바탕으로 한 첨단 유지관리 기술의 중요성이 점차 주목받고 있다. 이 연구에서는 머신러닝 기반의 의사결정나무 및 랜덤포레스트 분류 모델을 사용하여 교량의 안전등급을 예측하는 방법을 제안하였다. 일반국도상 교량 8,850개를 대상으로 해당 모델들을 혼동행렬, 균형 정확도, 재현율, ROC 곡선 및 AUC와 같이 여러가지 평가 지표를 통해 분석한 결과 전반적으로 랜덤포레스트가 의사결정나무보다 더 나은 예측 성능을 보유하였다. 특히 랜덤포레스트 중 랜덤 언더 샘플링 기법은 노후도가 비교적 커서 유지관리에 주의를 기울여야 하는 C, D등급 교량에 대해 재현율 83.4%로 다른 샘플링 기법들보다 예측 성능이 더 뛰어난 것으로 나타났다. 제안된 모델은 최근 점검이 실시되지 않은 교량들의 신속한 안전등급 파악 및 효율적이고 경제적인 유지관리 계획 수립에 유용하게 활용될 수 있을 것으로 기대된다.

Keywords

References

  1. Bektas, B. A., Carriquiry, A. and Smadi, O. (2013). "Using classification trees for predicting national bridge inventory condition ratings." Journal of Infrastructure Systems, Vol. 19, No. 4, pp. 425-433, https://doi.org/10.1061/(ASCE)IS.1943-555X.0000143.
  2. Chung, S. H., Lim, S. R. and Chi, S. H. (2016). "Developing an estimation model for safety rating of road bridges using rule-based classification method." Journal of KIBIM, Vol. 6, No. 2, pp. 29-38, https://doi.org/10.13161/kibim.2016.6.2.029 (in Korean).
  3. Dormann, C. F., Elith, J., Bacher, S., Buchmann, C., Carl, G., Carre, G., Marquez, J. R. G., Gruber, B., Lafourcade, B., Leitao, P. J., Munkemuller, T., McClean, C., Osborne, P. E., Reineking, B., Schroder, B., Skidmore, A. K., Zurell, D. and Lautenbach, S. (2013). "Collinearity: A review of methods to deal with it and a simulation study evaluating their performance." Ecography, Vol. 36, No. 1, pp. 27-46, https://doi.org/10.1111/j.1600-0587.2012.07348.x.
  4. Facility Management System(FMS) (2021). https://www.fms.or.kr/ com/mainForm.do (Accessed: September 12, 2021).
  5. Geron, A. (2019). Hands-on machine learning with Scikit-learn, Keras, and TensorFlow, 2nd Ed., O'Reilly Media, Inc.
  6. Grandini, M., Bagli, E. and Visani, G. (2020). Metrics for multi-class classification: An overview, arXiv:2008.05756, Available at: https://arxiv.org/abs/2008.05756 (Accessed: July 25, 2022).
  7. He, H. and Garcia, E. A. (2009). "Learning from imbalanced data." IEEE Transactions on Knowledge and Data Engineering, Vol. 21, No. 9, pp. 1263-1284, https://doi.org/10.1109/TKDE.2008.239.
  8. Hosmer, D. W. and Lemeshow, S. (2000). Applied logistic regression, 2nd Ed., John Wiley & Sons, Inc.
  9. Hur, Y. K., Lee, H. I., Shin, J. Y. and Park, C. H. (2010). "A research for the determinant factors of safety ratings in road-bridge." Journal of the Korea Institute for Structural Maintenance and Inspection, Vol. 14, No. 6, pp. 229-237, https://doi.org/10.11112/jksmi.2010.14.6.229 (in Korean).
  10. Kang, B. H. (2016). "Suggestions for improving the competitiveness of safety inspection industry." KSCE Magazine, Vol. 64, No. 10, pp. 12-15 (in Korean).
  11. Kang, S. H., Choi, S. I., Kim, H. R. and Lee, J. S. (2016). "A study on performance evaluation of infrastructure safety and maintenance." Korean Journal of Construction Engineering and Management, Vol. 17, No. 2, pp. 80-89, https://doi.org/10.6106/KJCEM.2016.17.2.080 (in Korean).
  12. Kazemitabar, S. J., Amini, A. A., Bloniarz, A. and Talwalker, A. (2017). "Variable importance using decision trees." Proceedings of the 31st International Conference on Neural Information Processing Systems(NIPS 2017), pp. 425-434.
  13. Kim, S. J. and Yoon, M. O. (2018). "A study on the improvement program of bridge safety management through public-private governance." Journal of the Korean Society of Hazard Mitigation, Vol. 18, No. 1, pp. 145-156, http://doi.org/10.9798/KOSHAM.2018.18.1.145 (in Korean).
  14. Korea Concrete Institute(KCI) (2009). Standard specification for concrete, KCI (in Korean).
  15. Lee, H. H., Kyung, K. S. and Jeon, J. C. (2010). "Fatigue life estimation method considering traffic properties for steel highway girder bridge." Journal of Korean Society of Steel Construction, Vol. 22, No. 3, pp. 209-218 (in Korean).
  16. Lee, H. H., Shin, B. G., Lee, Y. I. and Kim, Y. M. (2019a). "Suggestion of priority decision method for performance evaluation based on risk index for small and medium sized bridges." Journal of the Korea Institute for Structural Maintenance and Inspection, Vol. 23, No. 6, pp. 70-76, https://doi.org/10.11112/jksmi.2019.23.6.70 (in Korean).
  17. Lee, I. K. and Kim, D. H. (2015). "Highway bridge inspection period based on risk assessment." Journal of the Korea Institute for Structural Maintenance and Inspection, Vol. 19, No. 3, pp. 64-72, https://doi.org/10.11112/jksmi.2015.19.3.064 (in Korean).
  18. Lee, J. H., Lee, K. Y., Ahn, S. M. and Kong, J. S. (2018). "Proposal of maintenance scenario of feasibility analysis of bridge inspection using Bayesian approach." Journal of the Korean Society of Civil Engineers, Vol. 38, No. 4, pp. 505-516, http://doi.org/10.12652/Ksce.2018.38.4.0505 (in Korean).
  19. Lee, K. N., Lim, J. T., Bok, K. S. and Yoo, J. S. (2019b). "Handling method of imbalance data for machine learning: Focused on sampling." The Journal of the Korea Contents Association, Vol. 19, No. 11, pp. 567-577, https://doi.org/10.5392/JKCA.2019.19.11.567 (in Korean).
  20. Martinez, P., Mohamed, E., Mohsen, O. and Mohamed, Y. (2020). "Comparative study of data mining models for prediction of bridge future conditions." Journal of Performance of Constructed Facilities, Vol. 34, No. 1, 04019108, https://doi.org/10.1061/(ASCE)CF.1943-5509.0001395.
  21. Ministry of Land, Infrastructure and Transport(MOLIT) (2021a). Guidelines for safety and maintenance of facilities, MOLIT (in Korean).
  22. Ministry of Land, Infrastructure and Transport(MOLIT) (2021b). National bridge standard data, MOLIT, Available at: https://www.data.go.kr/data/15081953/fileData.do (Accessed: September 12, 2021) (in Korean).
  23. Ministry of Land, Infrastructure and Transport(MOLIT) (2021c). Special act on the safety control and maintenance of establishments, MOLIT (in Korean).
  24. Ministry of Land, Infrastructure and Transport(MOLIT) (2021d). Yearbook of road bridge and tunnel statistics, MOLIT, Available at: https://bti.kict.re.kr/bti/publicMain/main.do (Accessed: March 8, 2022) (in Korean).
  25. Nguyen, T. T. and Dinh, K. (2019). "Prediction of bridge deck condition rating based on artificial neural networks." Journal of Science and Technology in Civil Engineering, Vol. 13, No. 3, pp. 15-25, https://doi.org/10.31814/stce.nuce2019-13(3)-02.
  26. Oh, S. T., Lee, D. J. and Lee, J. H. (2010). "A condition rating method of bridges using an artificial neural network model." Journal of the Korean Society for Railway, Vol. 13, No. 1, pp. 71-77 (in Korean).
  27. Provost, F. and Fawcett, T. (2013). Data science of business: What you need to know about data mining and data-analytic thinking, O'Reilly Media, Inc.
  28. Ratner, B. (2009). "The correlation coefficient: Its values range between +1/-1, or do they?" Journal of Targeting, Measurement and Analysis for Marketing, Vol. 17, pp. 139-142, https://doi.org/10.1057/jt.2009.5.
  29. Scikit-learn developers (2007-2022). https://scikit-learn.org/.
  30. Truica, C. O. and Leordeanu, C. A. (2017). "Classification of an imbalanced data set using decision tree algorithms." U.P.B. Scientific Bulletin, Series C: Electrical Engineering and Computer Science, Vol. 79, Iss. 4, pp. 69-84.
  31. Yonhapnews (2023). Most of the bridges in the first new town have passed more than 30 years...Citizens are worried about deterioration. https://www.yna.co.kr/view/AKR20230406092900061 (Accessed: April 12, 2023) (in Korean).