International conference on construction engineering and project management (국제학술발표논문집)

  • 2024.07a
  • /
  • Pages.319-326
  • /
  • 2024
  • /
  • 2508-9048(eISSN)
Korea Institute of Construction Engineering and Management (한국건설관리학회)
권호 표지
DOI QR코드

DOI QR Code

Data mining approach for identifying factors impacting construction accident costs: from indirect expenses perspectives

  • Ayesha Munira CHOWDHURY (ICT Integrated Safety Ocean Smart Cities Engineering Department, Dong-A University) ;
  • Eun-Ju HA (Department of Electronics, Dong-A University) ;
  • Jae-ho CHOI (ICT Integrated Safety Ocean Smart Cities Engineering Department, Dong-A University)
  • Published : 2024.07.29
Download PDF
⟨ Previous Next ⟩

Abstract

Construction projects account for a significant proportion of workplace hazards globally. While construction cost reports typically emphasize direct accident costs such as treatment expenses, nursing care costs, or disability benefits, indirect factors like work interruption loss costs or consolation costs are frequently overlooked, because it is relatively difficult to estimate those factors in advance. Recognizing and accurately estimating the indirect costs factors associated with construction accidents would not only shed light on the monetary impact these incidents have on overall project costs but also would enable to estimate the total accident cost in advance. The current study seeks to identify factors influencing indirect costs, which ultimately govern the total accident cost, through a data mining approach. A survey was conducted in domestic construction companies, resulting in a dataset of 1038 accident records collected from construction sites. First, statistical analysis was performed to uncover characteristics and patterns of factors affecting construction accident costs from both direct and indirect perspectives. Later, this study proposes four distinct machine learning (ML) models, comparing their performances in predicting the total accident cost (including indirect costs) in advance. Additionally, this research sheds light on an important issue in construction data analysis, which is the scarcity of data in a particular class, by applying random oversampling and random undersampling techniques. The suggested framework can assist practitioners and management in estimating construction accident costs and identifying the relevant attributes that impact accidents at the construction site for future practices.

Keywords

Acknowledgement

This work is supported by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (National Research for Smart Construction Technology: Grant 225MIP-A156381-03), and the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2016R1A6A1A03012812).

References

  1. Y. Wang, H. Chen, B. Liu, M. Yang, and Q Long, "A Systematic Review on the Research Progress and Evolving Trends of Occupational Health and Safety Management: A Bibliometric Analysis of Mapping Knowledge Domains", Frontiers in Public Health, vol. 8, pp. 81, 2020. 
  2. Y. Shim, J. Jeong, J. Jeong, J. Lee, Y. Kim, "Comparative Analysis of the National Fatality Rate in Construction Industry Using Time-Series Approach and Equivalent Evaluation Conditions", Int. J. Environ. Res. Public Health, vol. 19, pp. 2312, 2022. 
  3. S. Kim, S. Cha, Y. Cha, & S. Han, "A Study on the Characteristics of Safety Insensitivity in Construction Workers", Korean Journal of Construction Engineering and Management, vol. 22, no. 2, pp. 88-96, 2021. 
  4. S.L. Tang, K.C. Ying, W.Y. Chan, and Y.L. Chan, "Impact of social safety investments on social costs of construction accidents", Construction Management and Economics, vol. 22, no. 9, pp. 937-946, 2004. 
  5. O. N. Aneziris, I. A. Papazoglou, D. Kallianiotis, "Occupational risk of tunneling construction," Safety Science, vol. 48, no. 8, pp. 964-972, 2010. 
  6. H.W. Heinrich, Industrial Accident Prevention: A Scientific Approach, 1st ed., New York, NY: McGraw Hill, 1931, pp. 2. 
  7. J. Hinze and L.L. Appelgate, "Costs of construction injuries", Journal of Construction Engineering and Management, vol. 117, no. 3, pp. 537-550, 1991 
  8. E. Leopold and S. Leonard, "Costs of construction accidents to employers," Occupational Accidents, 8, 1987. 
  9. J.G. Everret and B.P. Frank, "Costs of accidents and injuries to the construction industry," Journal of Construction Engineering and Management, pp. 158-164, 1996. 
  10. S.D. Choi, "A survey of the safety roles and costs of injuries in the roofing contracting industry," Journal of Safety, Health and Environmental Research, vol. 3, no. 1, pp. 1-20, 2006. 
  11. N.N.K.N.M. Azman, A.C. Ahmad, M.M. Derus, and I.F.M. Kamar, "Determination of direct to indirect accident cost Ratio for railway construction project," in MATEC Web of Conferences, vol. 266, p. 03009, EDP Sciences, 2019. 
  12. E.A.L. Teo and Y. Feng, "Costs of construction accidents to Singapore contractors," International Journal of Construction Management, vol. 11, no. 3, pp. 79-92, 2011. 
  13. S. W. Shin, "Construction safety and health management cost prediction model using support vector machine", Journal of the Korean Society of Safety, vol. 32, no. 1, pp.115-120. 
  14. B.U. Ayhan and O.B. Tokdemir, "Predicting the outcome of construction incidents," Safety Science, vol. 113, pp. 91-104, 2019. 
  15. T.Q.D. Pham, T. Le-Hong, X.V. Tran, "Efficient estimation and optimization of building costs using machine learning," International Journal of Construction Management, vol. 23, no. 5, pp. 909-921, 2023.