대한안전경영과학회지 (Journal of the Korea Safety Management & Science)

  • 제25권3호
  • /
  • Pages.63-71
  • /
  • 2023
  • /
  • 1229-6783(pISSN)
  • /
  • 2288-1484(eISSN)
대한안전경영과학회 (Korea Safety Management & Science)
권호 표지
DOI QR코드

DOI QR Code

건설 사고사례 데이터 기반 건설업 사망사고 요인분석

A Data-Driven Causal Analysis on Fatal Accidents in Construction Industry

  • 최지윤 (울산대학교 산업경영공학부) ;
  • 김시현 (울산대학교 산업경영공학부) ;
  • 이송이 (울산대학교 산업경영공학부) ;
  • 김경훈 (한국산업안전보건공단) ;
  • 이수동 (울산대학교 산업경영공학부)
  • Jiyoon Choi (Department of Industrial Engineering, University of Ulsan) ;
  • Sihyeon Kim (Department of Industrial Engineering, University of Ulsan) ;
  • Songe Lee (Department of Industrial Engineering, University of Ulsan) ;
  • Kyunghun Kim (Korea Occupational Safety and Health Agency) ;
  • Sudong Lee (Department of Industrial Engineering, University of Ulsan)
  • 투고 : 2023.08.22
  • 심사 : 2023.09.27
  • 발행 : 2023.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The construction industry stands out for its higher incidence of accidents in comparison to other sectors. A causal analysis of the accidents is necessary for effective prevention. In this study, we propose a data-driven causal analysis to find significant factors of fatal construction accidents. We collected 14,318 cases of structured and text data of construction accidents from the Construction Safety Management Integrated Information (CSI). For the variables in the collected dataset, we first analyze their patterns and correlations with fatal construction accidents by statistical analysis. In addition, machine learning algorithms are employed to develop a classification model for fatal accidents. The integration of SHAP (SHapley Additive exPlanations) allows for the identification of root causes driving fatal incidents. As a result, the outcome reveals the significant factors and keywords wielding notable influence over fatal accidents within construction contexts.

키워드

과제정보

이 논문은 2023년도 한국산업단지공단의 재원으로 울산 스마트제조고급인력양성사업의 지원을 받아 수행된 연구임

참고문헌

  1. S. G. Lee(2018), "A study on the trends of construction safety accident in unstructured text using topic modeling." Journal of the Korea Academia-Industrial Cooperation Society, 19(10):176-182. https://doi.org/10.5762/KAIS.2018.19.10.176
  2. K. Park, H. Kim(2021), "Analysis of seasonal importance of construction hazards using text mining." Journal of the Korean Society of Civil Engineers, 41(3):305-316.
  3. F. Zhang, H. Fleyeh, X. Wang, M. Lu(2019), "Construction site accident analysis using text mining and natural language processing techniques." Automation in Construction, 99:238-248. https://doi.org/10.1016/j.autcon.2018.12.016
  4. Y. C. Kim, W. S. Yoo, Y. S. Shin(2017), "Application of artificial neural networks to prediction of construction safety accidents." Journal of the Korean Society of Hazard Mitigation, 17(1):7-14. https://doi.org/10.9798/KOSHAM.2017.17.1.7
  5. J. H. Jo(2012), "A study on the causes analysis and preventive measures by disaster types in construction fields." Journal of the Korea Safety Management & Science, 14(1):7-13. https://doi.org/10.12812/ksms.2012.14.1.007
  6. S. J. Choi, J. H. Kim, K. Jung,(2021), "Development of prediction models for fatal accidents using proactive information in construction sites." Journal of the Korean Society of Safety, 36(3):31-39. https://doi.org/10.14346/JKOSOS.2021.36.3.31
  7. Y. Cho, Y. C. Kim, Y. Shin(2017), "Prediction model of construction safety accidents using decision tree technique." Journal of the Korea Institute of Building Construction, 17(3):295-303. https://doi.org/10.5345/JKIBC.2017.17.3.295
  8. Q. Xu, K. Xu(2021), "Analysis of the characteristics of fatal accidents in the construction industry in China based on statistical data." International Journal of Environmental Research and Public Health, 18(4):2162.
  9. B. Hola, T. Nowobilski, I. Szer, J. Szer(2017), "Identification of factors affecting the accident rate in the construction industry." Procedia Engineering, 208:35-42. https://doi.org/10.1016/j.proeng.2017.11.018
  10. N. Udawatta, R. Rameezdeen(2012), Fatalities and non-fatalities in construction accidents. Deakin University. https://hdl.handle.net/10536/DRO/DU:30088163
  11. M. Amiri, A. Ardeshir, M. H. Fazel Zarandi, E. Soltanaghaei(2016), "Pattern extraction for high-risk accidents in the construction industry: A data-mining approach." International Journal of Injury Control and Safety Promotion, 23(3):264-276. https://doi.org/10.1080/17457300.2015.1032979
  12. M. Cho, D. Lee, J. Park, S. Park(2022), "Development of machine learning-based construction accident prediction model using structured and unstructured data of construction sites." KSCE Journal of Civil and Environmental Engineering Research, 42(1):127-134. https://doi.org/10.12652/KSCE.2022.42.1.0127
  13. S. M. Lundberg, S. I. Lee(2017), "A unified approach to interpreting model predictions." Advances in Neural Information Processing Systems, 30.
  14. T. Chen, C. Guestrin(2016, August), "Xgboost: A scalable tree boosting system." Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, pp. 785-794.
  15. S. K. TBrain(2019), Korean BERT pre-trained cased (KoBERT). https://github.com/SKTBrain/KoBERT
  16. E. L. Park, S. Cho(2014, October), "KoNLPy: Korean natural language processing in Python." Proceedings of the 26th Annual Conference on Human & Cognitive Language Technology, Chuncheon, Korea, 6:133-136.
  17. T. Akiba, S. Sano, T. Yanase, T. Ohta, M. Koyama(2019, July), "Optuna: A next-generation hyperparameter optimization framework." Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2623-2631.