대한건축학회논문집 (Journal of the Architectural Institute of Korea)

  • 제38권4호
  • /
  • Pages.237-244
  • /
  • 2022
  • /
  • 2733-6239(pISSN)
  • /
  • 2733-6247(eISSN)
대한건축학회 (Architectural Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

건설 재해사례 보고서의 텍스트 마이닝을 통한 복합사고 패턴 분석

Analyzing Patterns of Multi-cause Accidents From KOSHA's Construction Injury Case Reports Utilizing Text Mining Methodology

  • 김하영 (이화여대 건축도시시스템공학과) ;
  • 이준성 (이화여대 건축도시시스템공학과) ;
  • 장예은 (이화여대 건축도시시스템공학과)
  • Kim, Hayoung (Dept. of Architectural & Urban Systems Engineering, Ewha Womans University) ;
  • Yi, June-Seong (Dept. of Architectural & Urban Systems Engineering, Ewha Womans University) ;
  • Jang, YeEun (Dept. of Architectural & Urban Systems Engineering, Ewha Womans University)
  • 투고 : 2022.02.04
  • 심사 : 2022.04.05
  • 발행 : 2022.04.30
⟨ 이전 논문 다음 논문 ⟩

초록

Construction accidents usually involve two or more injuries in succession considering various risk factors are present everywhere on site. This study aims to analyze the patterns of these multi-cause accidents through a text mining methodology. There were 1,300 accident reports from the Korea Occupational Safety & Health Agency (KOSHA). The collected data was refined and processed through a morpheme analyzer for semantic analysis. A Python algorithm was developed and applied to extract multi-cause accidents; 139 out of 987 accident cases were extracted. The occurrence patterns involving the 139 multi-cause accidents were based on the relationship of each accident type and the occurrence characteristics by type. The type of multi-cause accidents that occurred at the highest frequency were the narrowness or winded (Type 2) or fall (Type 1) due to the fall down or overturn (Type 5) of an object or structure. The rate of acting as a primary and secondary accident differed depending on the accident type. Falling (Type 1) and narrowness or winded (Type 2) had a very high proportion of secondary accidents, while the flying object, collision, fall down or overturn and collapse (Type 3, 4, 5 and 6, respectively) were more likely to act as primary accidents. Using the results from this study, once a specific accident is recognized, the scale of the accident can be minimized by closely examining the occurrence of similar accidents and possibly prevent future occurrences. Additionally, this study can provide direction to review data classified as a single accident from past instances.

키워드

과제정보

본 연구는 국토교통부/국토교통과학기술진흥원의 지원으로 수행 되었음(과제번호 22 ORPS-B158109-03).

참고문헌

  1. Caldas, C.H., Soibelman, L., & Han, J. (2002). Automated Classification of Construction Project Documents, Journal of Computing in Civil Engineering, 16(4), 234-243. https://doi.org/10.1061/(ASCE)0887-3801(2002)16:4(234)
  2. Ha, S., Kim, T., Son, K., Kim, T., & Son, S. (2018). Quantification Model Development of Human Accidents based on the Insurance Claim Payout on Construction Site, Journal of the Korea Institute of Building Construction, 18(2), 151-159. https://doi.org/10.5345/JKIBC.2018.18.2.151
  3. Heinrich, H.W. (1941). Industrial Accident Prevention: A Scientific Approach, 2nd ed.
  4. Kim, H., Jang, Y., Kang, H., Son, J., & Yi, J. (2021). A Suggestion of the Direction of Construction Disaster Document Management through Text Data Classification Model based on Deep Learning, Korean Journal of Construction Engineering and Management, 22(5), 73-85. https://doi.org/10.6106/KJCEM.2021.22.5.073
  5. Kim, S. (2019). A Study on the Reduction Measurement in Construction Fall Deaths: Focusing on small construction sites of 50 persons or less, Thesis, Kyonggi University.
  6. Kim, Y., Kim, J., & Kim. H. (2021). Artificial intelligence related to safety and disasters in the construction industry, Korea Institute of Construction Engineering and Management, 22(4), 4-8.
  7. Kim, J. (2015). Factor Analysis of Workers Accidents in Construction Site Using Big Data Approach, Thesis, Yeungnam University.
  8. Korea Occupational Safety and Health Agency (2016). Guidelines for industrial accident record/classification.
  9. Ko, E., & Kim, N. (2018). Automatic Quality Evaluation with Completeness and Succinctness for Text Summarization, Journal of Intelligence and Information Systems, 24(2), 125-148. https://doi.org/10.13088/JIIS.2018.24.2.125
  10. Lee, J. (2021). A study on data processing and accident prediction modeling based on machine learning methods for occupational accident analysis in the construction industry, Thesis, Incheon National University.
  11. Lim, W. (2020). A study on the analysis of construction accidents through the application of accident analysis model, Thesis, Seoul National University of Science and Technology.
  12. Moon, J. (2019). A study on the analysis of occupational incident cases in construction site using big data analysis technique, Thesis, University of Seoul.
  13. Ministry of Employment and Labor (2021). Statistics of Industrial accident 2020.
  14. Park, H., Song, M., & Shin, K. (2018). Sentiment Analysis of Korean Reviews Using CNN: Focusing on Morpheme Embedding, Korea Intelligent Information Systems Society, 24(2), 59-83.
  15. Park, J. (2017). A study on the government policy reforms for reduction of the industrial disasters on the construction spots: in comparison with the United States, Thesis, Yonsei University.
  16. Park, J. (2021). A Study on Availability of Text mining in Knowledge Management of Construction Corporations, Thesis, Hanyang University.
  17. Park, J. (2017). A study on the government policy reforms for reduction of the industrial disasters on the construction spots: in comparison with the United States, Thesis, Yonsei University.
  18. Park, K., & Kim, H. (2021). Analysis of Seasonal Importance of Construction Hazards Using Text Mining, Korean Society of Civil Engineering, 41(3), 305-316.
  19. Seoul Institute of Technology (2021). Analysis of Risk Types and Improvement of Safety Management System for Workers in Construction Sites.
  20. Tixier, A.J.-P., Hallowell, M.R., Rajagopalan, B., & Bowman, D. (2016). Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports, Automation in Construction, 62, 45-56. https://doi.org/10.1016/j.autcon.2015.11.001