Journal of the Korea Safety Management & Science (대한안전경영과학회지)

Korea Safety Management & Science (대한안전경영과학회)
권호 표지
DOI QR코드

DOI QR Code

Socio-economic Indicators Based Relative Comparison Methodology of National Occupational Accident Fatality Rates Using Machine Learning

머신러닝을 활용한 사회 · 경제지표 기반 산재 사고사망률 상대비교 방법론

  • Kyunghun, Kim (Department of Occupational Safety and Health, University of Ulsan) ;
  • Sudong, Lee (Department of Occupational Safety and Health, University of Ulsan)
  • 김경훈 (울산대학교 산업안전보건전문학과) ;
  • 이수동 (울산대학교 산업안전보건전문학과)
  • Received : 2022.11.17
  • Accepted : 2022.12.23
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

A reliable prediction model of national occupational accident fatality rate can be used to evaluate level of safety and health protection for workers in a country. Moreover, the socio-economic aspects of occupational accidents can be identified through interpretation of a well-organized prediction model. In this paper, we propose a machine learning based relative comparison methods to predict and interpret a national occupational accident fatality rate based on socio-economic indicators. First, we collected 29 years of the relevant data from 11 developed countries. Second, we applied 4 types of machine learning regression models and evaluate their performance. Third, we interpret the contribution of each input variable using Shapley Additive Explanations(SHAP). As a result, Gradient Boosting Regressor showed the best predictive performance. We found that different patterns exist across countries in accordance with different socio-economic variables and occupational accident fatality rate.

Keywords

References

  1. S. J. Choi, K. H. Jung(2021), "Statistical analysis of major accident reports and development of a real-time detection model for portable ladder and safety helmet." KSMS, 23(1):9-15.
  2. A. B. Parsa, A. Movahedi, et al.(2020), "Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis." Accident Analysis & Prevention, 136.
  3. D. Sheng, A. Khattak, et al.(2022), "Predicting and analyzing road traffic injury severity using boosting-Based ensemble learning models with shapley additive explanations." International Journal of Environmental Research and Public Health, 19(5):2925. https://doi.org/10.3390/ijerph19052925
  4. K. Wang, J. Tian, C. Zheng, et al.(2021), "Interpretable prediction of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease based on machine learning and SHAP." Computers in Biology and Medicine, 137.
  5. T. Seki, Y. Kawazoe, et al.(2021), "Machine learning-based prediction of in-hospital mortality using admission laboratory data: A retrospective, single-site study using electronic health record data." PLoS One, 16(2):e0246640. https://doi.org/10.1371/journal.pone.0246640
  6. Y. Gao, G. Y. Cai, et al.(2020), "Machine learning based early warning system enables accurate mortality risk prediction for COVID-19." Nat Commun, 11:5033. https://doi.org/10.1038/s41467-020-18684-2
  7. P. Y. Tseng, Y. T. Chen, et al.(2020), "Prediction of the development of acute kidney injury following cardiac surgery by machine learning." Crit Care, 24:478. https://doi.org/10.1186/s13054-020-03179-9
  8. R. Li, A. Shinde, et al.(2020), "Machine learning-based interpretation and visualization of nonlinear interactions in prostate cancer survival." JCO Clinical Cancer Informatics, 4:637-646.
  9. J. Hegde, B. Rokseth(2020), "Applications of machine learning methods for engineering risk assessment-A review." Safety Science, 122.
  10. F. Sattari, F. Macciotta, et al.(2021), "Application of Bayesian network and artificial intelligence to reduce accident/incident rates in oil & gas companies." Safety Science, 133.
  11. H. Baker, M. R. Hallowell, et al.(2020), "AI-based prediction of independent construction safety outcomes from universal attributes." Automation in Construction, 118.
  12. M. Pishgar, S. F. Issa, et al(2021), "A novel framework to review artificial intelligence and its applications in occupational safety and health." Int J Environ Res Public Health, 18(13):6705. https://doi.org/10.3390/ijerph18136705
  13. K. Koc, O. Ekmekcioglu, et al.(2022), "Accident prediction in construction using hybrid wavelet-machine learning." Automation in Construction, 133.
  14. J. Mohammed, M. J. Mahmud(2020), "Selection of a machine learning algorithm for OSHA fatalities." TEMSCON, 1-5.
  15. A. Gondia, M. Ezzeldin, et al.(2022), "Machine learning-based decision support framework for construction injury severity prediction and risk mitigation." ASCE, 8(3).
  16. H. R. Oh, A. L. Son, et al.(2021), "Occupational accident prediction modeling and analysis using SHAP." Journal of Digital Contents Society, 22: 1115-1123. https://doi.org/10.9728/dcs.2021.22.7.1115
  17. J. H. Kim, J. E. Kim, et al.(2021), "Machine learning-based models for accident prediction at a Korean container port." Sustainability, 13(16): 9137. https://doi.org/10.3390/su13169137
  18. J. Takala, et al.(2014), "Global estimates of the burden of injury and illness at work in 2012." J. Occup Environ Hyg. 11(5):326-37. https://doi.org/10.1080/15459624.2013.863131