DOI QR코드

DOI QR Code

Association Rules Analysis of Safe Accidents Caused by Falling Objects

낙하물에 기인한 안전사고의 연관규칙 분석

  • Son, Ki-Young (School of Architectural Engineering, University of Ulsan) ;
  • Ryu, Han-Guk (Department of Architecture, Sahm Yook University)
  • Received : 2019.05.09
  • Accepted : 2019.07.10
  • Published : 2019.08.20

Abstract

Construction industry is one of the most dangerous industry. As the construction accidents occur due to the repeated factors found in each accidents, there is a limitation in analyzing all types of occupational accidents by the existing descriptive analysis and statistical test. In this study, we classified safety accidents caused by falling objects among the accident types occurring at construction sites into fatal and nonfatal accidents and deduced the factors. In addition, we deduced the association rules among the safety accidents factors caused by falling objects through the association rule analysis method among the machine learning techniques. Therefore, considering the association rules for fatal and nonfatal accidents proposed in this study, it would be possible to prevent accidents by searching for countermeasures against safety accidents caused by falling objects.

건설업은 전체 산업 중에서 가장 많은 재해자를 발생시키는 산업 분야이다. 각 재해에서 발견되는 반복되는 요인들로 인해 재해가 발생하기 때문에 기존의 기술통계 분석 및 통계적 검정으로 업무상 재해 유형을 분석하는 데 한계가 있다. 이에 본 연구는 건설현장에서 발생하는 재해 유형 중 낙하물에 기인한 안전사고에 대하여 사망과 부상 사고로 구분하여 사고 원인들을 도출한다. 또한, 기계학습 기법 중 연관 규칙 분석 방법을 통하여 낙하물에 기인한 안전사고의 규칙을 발견하고, 낙하물의 요인들을 군집하여 중점 재해요인을 도출한다. 본 연구에서 제안한 낙하물에 기인한 사망과 부상 사고에 대한 규칙을 감안하여 낙하물에 기인한 안전사고에 대한 대처방안을 모색하면 보다 정확한 사고예방이 가능할 것으로 판단된다.

Keywords

GCSGBX_2019_v19n4_341_f0001.png 이미지

Figure 1. Methodology

GCSGBX_2019_v19n4_341_f0002.png 이미지

Figure 2. Data representation for the model

GCSGBX_2019_v19n4_341_f0003.png 이미지

Figure 3. Frequent words

GCSGBX_2019_v19n4_341_f0004.png 이미지

Figure 4. Scatter plot for association rules

GCSGBX_2019_v19n4_341_f0005.png 이미지

Figure 5. A dendrogram example of nonfatal and fatal accidents grouping caused by fall objects

Table 1. Data outline

GCSGBX_2019_v19n4_341_t0001.png 이미지

Table 2. Result of association rules based on fatal

GCSGBX_2019_v19n4_341_t0002.png 이미지

Table 3. Result of association rules based on nonfatal

GCSGBX_2019_v19n4_341_t0003.png 이미지

Table 4. Summary of hierarchical clustering result based on the input variables

GCSGBX_2019_v19n4_341_t0004.png 이미지

References

  1. Ministry of Employment and Labor. 2017 Industrial disaster status analysis. Sejong Metropolitan Autonomous City(Korea): Ministry of Employment and Labor; 2018. 732 p.
  2. Ministry of Employment and Labor. Collection and payment of workers' compensation insurance for e-country indicators [Internet]. Sejong Metropolitan Autonomous City(Korea): Ministry of Employment and Labor; 2016 [updated 2018 Mar 26; cited 2019 Mar 9]. Available from : http://www.index.go.kr/potal/main/EachDtlPageDetail.do?idx_cd=2742
  3. Statics Korea. Number of fatal industrial accidents per 100,000 workers(OECD)[Internet]. Daejeon Metropolitan City(Korea): Statics Korea; 2017 [updated 2018 Oct 10; cited 2019 Mar 10]. Available from : http://kosis.kr/statHtml/statHtml.do?orgId=101&tblId=DT_2KAA308_OECD
  4. Jo JH, Woo HS, Park MK. An empirical study on the influence of industrial safety education to workers in construction field: Focus on the supervisor and the worker. Journal of Korea Safety Management & Science. 2009 Dec;2(1):43-55.
  5. Ahn YS. Study on the analysis of present situation and improvement direction of construction safety empirical education. Journal of the Korea Institute of Building Construction. 2008 Aug;8(4):95-103. https://doi.org/10.5345/JKIC.2008.8.4.095
  6. Paik SW, Kim HJ, Choi DH. A study of decreasing critical disaterous accidents in small construction sites. Journal of the Korean Society of Agricultural Engineers. 2012 Nov;54(6):121-31. http://dx.doi.org/10.5389/KSAE.2012.54.6.121
  7. Kim YK, Kim JD, Kim GH. A comparison of the ranking for safety motivations factors between construction engineers and construction managers. Journal of the Korea Institute of Building Construction. 2019 Jun;19(3):247-54. https://doi.org/10.5345/JKIBC.2019.19.3.247
  8. Kim JM, Lee JB, Chang SR. A study of the accident analysis of architectural work. Journal of the Korean Society of Safety. 2012 Jun;31(3):96-101. http://dx.doi.org/10.14346/JKOSOS.2016.31.3.96
  9. Jo JH. A study on the causes analysis and preventive measures by disaster types in construction fields. Journal of Korea Safety Management & Science. 2012 Mar;14(1):7-13. https://doi.org/10.12812/ksms.2012.14.1.007
  10. Jang CH, Lee JS. Risk assessment of dropped object in offshore engineering through quantified risk analysis. Journal of the Society of Naval Architects of Korea. 2017 Apr;54(2):143-50. https://doi.org/10.3744/SNAK.2017.54.2.143
  11. Jeon HW, Jung IS, Lee CS. Risk assessment for reducing safety accidents caused by construction machinery. Journal of the Korean Society of Safety. 2013 Oct;28(6):65-72. https://doi.org/10.14346/JKOSOS.2013.28.6.064
  12. Agrawal R, Imielinski T, Swami A. Mining association rules between sets of items in large database. In ACM Sigmod Record. 1993 May;22(2):207-16. https://doi.org/10.1145/170036.170072
  13. Agrawal R, Srikant R. Fast algorithms for mining association rules. Proceedings of the 20th Very Large Data Bases Conference; 1994 Sep 12-15; Santiago, Chile: VLDB; 1994. p. 487-99.
  14. Weng J, Zhu JZ, Yan X, Liu Z. Investigation of work zone crash casualty patterns using association rules. Accident Analysis & Prevention. 2016 Jul;92:43-52. https://doi.org/10.1016/j.aap.2016.03.017
  15. Cheng CW, Lin CC, Leu SS. Use of association rules to explore cause-effect relationships in occupational accidents in the Taiwan construction industry. Safety science. 2010 Apr;48(4):436-44. https://doi.org/10.1016/j.ssci.2009.12.005
  16. Li H, Li X, Luo X, Siebert J. Investigation of the causality patterns of non-helmet use behavior of construction workers. Automation in Construction, 2017 Aug;80:95-103. https://doi.org/10.1016/j.autcon.2017.02.006
  17. Shmueli G, Bruce PC, Patel NR. Data mining for business intelligence: concepts, techniques, and applications with XLMINER. 3rd ed. Hoboken, NJ: Wiley; 2016. 509 p.
  18. Muller A, Guido S. Introduction to machine learning with python. Sebastopol, CA: O'reilly; 2016. 447 p.