DOI QR코드

DOI QR Code

Analysis of the Feature Importance of Occupational Accidents Occurring at Construction Sites on the Severity of Lost Workdays

건설 현장에서 발생한 업무상 재해가 근로손실일수 심각도에 미치는 특징 중요도 분석

  • Kang, Kyung-Su (Construction Engineering and Management Institute, Sahmyook University) ;
  • Choi, Jae-Hyun (School of Architecturral Engineering, Korea University of Technology and Education (Koreatech)) ;
  • Ryu, Han-Guk (Department of Architectural, Sahmyook University)
  • Received : 2021.03.16
  • Accepted : 2021.04.09
  • Published : 2021.04.20

Abstract

The construction industry causes the most accidents and fatalities among all industries. Although many efforts have been made to reduce safety accidents in construction, the study on the lost workdays that return to work place is insufficient. Therefore, this study proposes a model that classifies the lost workdays lost into moderate and severity, and derives the importance of variable and analyzes important factors through the trained random forest model. We analyze the learning process of the random forest which is a black box model, and extracted important variables that impact on the severity of the lost workdays through the extracted feature importance. The factors existing inside were analyzed through the extracted variables. The purpose of this study is to analyze the accident case data at the construction site through a random forest model and to review variables that have a high impact on the lost workdays. In the future, this sutdy can apply to improve construction safety management and reduce the accident of industrial accidents.

건설업은 전체 산업 분야 중에서 가장 많은 재해와 사망자를 발생시키는 산업 분야이다. 건설안전 재해를 줄이기 위한 큰 노력이 진행되어왔지만, 사망사고를 제외한 근로자의 업무복귀시간까지 회복되는 근로손실일수에 관한 연구는 매우 적은 편이다. 따라서 본 연구는 근로손실일수를 심각도로 정의하여 이를 분류하는 모형을 제안하고 학습된 모형을 통해 특징 중요도를 도출하고 중요한 특징을 분석하고자 하였다. 블랙박스 모형인 랜덤 포레스트의 학습 과정을 해석하고 추출된 특징 중요도를 통해 근로손실일수 심각도에 영향력을 행사하는 중요 변수를 추출하였다. 추출된 특징을 통해 내부에 존재하는 요인들을 분석하였다. 본 연구의 목적은 건설 현장에서 발생한 사고 사례 데이터를 랜덤 포레스트 모형을 통해 분석하고자 하였다. 근로손실일수의 심각도에 미치는 중요한 특징을 도출해 체계적으로 관리한다면 건설 재해를 예방할 수 있다.

Keywords

References

  1. Occupational Safety & Health Research Institute. Analysis of Industrial Accidents in 2019. Ulsan (Korea): Korea Occupational Safety and Health Agency; 2020. p. 7-640.
  2. Kang KS, Ryu HG. Predicting types of occupational accidents at construction sites in Korea using random forest model. Safety Science. 2019 Dec;120:226-36. https://doi.org/10.1016/j.ssci.2019.06.034
  3. Ale BJM, Bellamy LJ, Baksteen H, Damen M, Goossens LHJ, Hale AR, Mud M, Papazoglou IA, Whiston JY. Accidents in the construction industry in the netherlands: An analysis of accident reports using storybuilder. Reliability Engineering & System Safety. 2008 Oct;93(10):1523-33. https://doi.org/10.1016/j.ress.2007.09.004
  4. Swuste P, Frijters A, Guldenmund F. Is it possible to influence safety in the building sector?: A literature review extending fro m 1980 until the present. Safety science. 2012 Jun;50(5):1333-43. https://doi.org/10.1016/j.ssci.2011.12.036
  5. Liao CW, Perng YH. Data mining for occupational injuries in the Taiwan construction industry. Safety science. 2008 Aug;46(7):1091-102. https://doi.org/10.1016/j.ssci.2007.04.007
  6. Winge S, Albrechtsen E. Accident types and barrier failures in the construction industry. Safety science. 2018 Jun;105:158-66. https://doi.org/10.1016/j.ssci.2018.02.006
  7. Hosseinian SS, Torghabeh ZJ. Major theories of construction accident causation models: A literature review. International Journal of Advances in Engineering & Technology. 2012 Sep;4(2):53-66.
  8. Lopez-Alonso M, Ibarrondo-Davila MP, Rubio-Gamez MC, Munoz TG. The impact of health and safety investment on construction company costs. Safety science. 2013 Dec;60:151-9. https://doi.org/10.1016/j.ssci.2013.06.013
  9. Santana VS, Villaveces A, Bangdiwala SI, Runyan CW, Albuquerque-Oliveira PR. Workdays lost due to occupational injuries among young workers in Brazil. American journal of industrial medicine. 2012 Oct;55(10):917-25. https://doi.org/10.1002/ajim.22099. Epub 2012 Jul 27
  10. Manu P, Ankrah N, Proverbs D, Suresh S. An approach for deter mining the extent of contribution of construction project features to accident causation. Safety Science. 2010 Jul;48(6):687-92. https://doi.org/10.1016/j.ssci.2010.03.001
  11. Boden LI, Biddle EA, Spieler EA. Social and economic impacts of workplace illness and injury: current and future directions for research. American Journal of Industrial Medicine. 2001 Oct;40(4):398-402. https://doi.org/10.1002/ajim.10013
  12. Cho YR, Kim YC, Shin YS. Prediction model of construction safety accidents using decision tree technique. Journal of the Korea Institute of Building Construction. 2017 Jun;17(3):295-303. https://doi.org/10.5345/JKIBC.2017.17.3.295
  13. Kim YC, Yoo WS, Shin YS. Application of artificial neural networks to prediction of construction safety accidents. The Journal of the Korean Society of Hazard Mitigation. 2017 Fed;17(1):7-14. https://doi.org/10.9798/KOSHAM.2017.17.1.7
  14. Kim EJ. Prediction model for construction safety accidents using random forest. Journal of The Regional Association of Architectural Institute of Korea. 2020 Oct;22(5):81-7.
  15. Weil D. Valuing the economic consequences of work injury and illness: a comparison of methods and findings. American Journal of Industrial Medicine. 2001 Oct;40(4):418-37. https://doi.org/10.1002/ajim.1114
  16. Jeong WI, Lee KS, Jeon YI. Occupational accidents and foregone working days. Journal of Korean Economics Studies. 2011 Jun;29(2):139-74.
  17. Choi JW, Kim TW, Lee CS. Effects of weather factors on the work loss days of the elderly workers. Korean Journal of Construction Engineering and Management. 2019 Jan;20(1):41-51. https://doi.org/10.6106/KJCEM.2019.20.1.041
  18. Lee DB, Lee TY, Jo YC, Lee YS, Sim UT. Analysis of absenteeism factors of workers in manufacturing industries. Industrial Health. 1995 May;85:2-9.
  19. Yoon JH, Jang SR, Im HK. Occupational accident prevention policy for middle-aged and old workers according to the trend of occupational accident. Ergonomics Society of Korea 2008 Conference; 2008 May 23; Gumi-si, Korea. Seoul (Korea): Ergonomics Society of Korea; 2008. p. 8-11.
  20. Korea Health Industry Development Institute. Hospital management status survey - The average number of hospital stays for inpatients by type of salary [Internet]. Cheongju (Korea): Korea Health Industry Development Institute; 2015 Set 30. Available from: https://kosis.kr/statHtml/statHtml.do?orgId=358&tblId=DT_358N_H409101
  21. Jeong WM, Park CY, Koo JW, Roh YM. Predictors of return to work in occupational injured workers. Annals of Occupational and Environmental Medicine 2003;15(2):119-31.
  22. Jo JH. A study on the Causes Analysis and Preventive Measures by Disaster types in Construction Fields. Conference of Korea Safety Management and Science; 2011 Nov; Cheonan-si, South Korea. Incheon (Korea): Korea Safety Management and Science; 2011. p. 23-34.
  23. Ruser JW. The changing composition of lost-workday injuries. Monthly Labor Review. 1999 Jun;122(6):11-9.
  24. Health and Safety Executive. Working days lost in Great Britain [Internet]. Merseyside (England): Health and Safety Executive; 2017. Available from: http://www.hse.gov.uk/statistics/dayslost.htm
  25. Yang YS, Park JH, Lee CS. Accident risk analysis of construction workers by occupation. Journal of the Architectural Institue of Korea Structure & Construction. 2009;25(10):149-56.
  26. Kim SG, An HY, Lee EH. A comparative study on the changes in indicators of occupational accidents and social and economic activities in OECD countries. Ulsan-si (Korea): Occupational Safety and Health Research Institute. 2009 Dec. Report No.: 2009-72-1264.
  27. Kotsiantis SB. Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering. 2007 Jun;160:3-24.
  28. Breiman L, Friedman J, Olshen R, Stone C. Classification and regression trees. CRC press. 1984. p. 237-51.
  29. Geron A. Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems. 1st ed. Sebastopol (CA): O'Reilly Media. 2017. p. 189-211.
  30. David D. Summing feature importance in Scikit-learn for a set of features [Internet]. StackExchange; 2017 [updated 2020 Sep 11; cited 2021 Feb 12]. Available from: http://bit.ly/2TYUjnu
  31. Breiman L. Random forests. Machine learning. 2001 Oct;45(1):5-32. https://doi.org/10.1023/A:1010933404324
  32. Parr T, Turgutlu K, Csiszar C, Howard J. Beware Default Random Forest Importances. explained.ai [Preprint]. 2018 [cited 2021 Feb 12]. Available from: https://explained.ai/rf-importance/
  33. U.S. Bureau of Labor Statistics. Employer-Reported Workplace Injuries and Illnesses (Annual) News Release [Internet]. U.S. Department of Labor, Washington (DC): U.S. Bureau of Labor Statistics; 2020 Apr 11 [updated 2020 Nov 4; cited 2021 Feb 28]. Available from: https://www.bls.gov/news.release/osh.htm