Journal of the Architectural Institute of Korea (대한건축학회논문집)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

A Model to Predict Occupational Safety and Health Management Expenses in Construction Applying Multi-variate Regression Analysis and Deep Neural Network

다중회귀분석과 DNN 알고리즘 기반 산업안전보건관리비 예측 모델 제안

  • Received : 2021.05.27
  • Accepted : 2021.09.10
  • Published : 2021.09.30
⟨ Previous Next ⟩

Abstract

To reduce safety accidents leading to serious casualties and compensation, the Ministry of Employment and Labor prescribes Occupational Safety and Health Management Expenses (OSHME). Though there is an expense calculated by fixed rate, it is more urgent to spend the set amount according to the situation rather than standards due to the ambiguous criteria. Consequently, OSHME used nominally to make contract rather than to educate and protect the safety of workers. Therefore, in this research, OSHME was predicted by applying Deep Neural Network (DNN) with various optimizer, epoch, nodes based on 135 general construction cases under 500 million won to compare from multivariate regression analysis and origin contract cost multiplied existing rate by applying error indicators, mean squared error (MSE) and mean absoloute error (MAE). As a result, by comparing the values from three different analysis, DNN model with bayesian regularization optimizer in 0.01 learning rate was outstanding method to predict OSHME. Rather than simply executing as the current law, multiplying direct labor and material costs by a certain percentage, proposed model would support to calculate construction costs efficiently. Especially, as the contract material costs show high impact on consumed OSHME, when the sum of labor and material costs is the same, if material costs are high, it is required that OSHME be set higher. Furthermore, it is necessary to specify clear criteria and detailed usage plans to ensure not to execute incorrectly.

Keywords

References

  1. An, B. Y., & Song, T. S. (2020). A Study on Improving the Occupational Safety and Health Management Cost Calculation Standards. In Proceedings of the Korean Institute of Building Construction Conference (pp. 169-170). The Korean Institute of Building Construction.
  2. An, H. J., Park, S. M., Lee, J. H., & Kang, L. K. (2020). study on the application of deep learning model for estimation of activity duration in railway construction project. Journal of the Korean Railroad Association, 23 (7) and 615-624.
  3. Bae, S., & Yu, J. (2018). Estimation of the Apartment Housing Price Using the Machine Learning Methods: The Case of Gangnam-gu. Seoul. J. Korea Real Estate Anal. Assoc, 24, 69-85.
  4. Bae, S. W., & Yu, J. S. (2017). Predicting the Real Estate Price Index Using Deep Learning. Real Estate Research, 27, 71-86.
  5. Baek, J. W., & Chung, K. (2020). Context deep neural network model for predicting depression risk using multiple regression. IEEE Access, 8, 18171-18181. https://doi.org/10.1109/ACCESS.2020.2968393
  6. Baek, J., & Ock, J. (2019). A Study on the Application Method of Construction Site Direct Construction System-Centered on domestic construction case. Jouranl of the Architectural Institute of Korea Structure & Construction, 35(11), 171-180.
  7. Baek, Y., Wee, K., Baek, I., & Kim, J. (2020). A Study on Improvement of Occupational Safety and Health Mangement Cost Accounting Standards. Korean Journal of Construction Engineering and Management, 21(2), 39-46. https://doi.org/10.6106/KJCEM.2020.21.2.039
  8. Chae, Y. S., Yoon, Y. G., & Oh, T. K. (2018). A Study on the Proper Rate of the Safety Management Cost under the Construction Technology Promotion Act by Direct Calculation. Journal of the Korean Society of Safety, 33(2), 68-75. https://doi.org/10.14346/JKOSOS.2018.33.2.68
  9. Chel, H., Majumder, A., & Nandi, D. (2011). Scaled conjugate gradient algorithm in neural network based approach for handwritten text recognition. In International Conference on Computational Science, Engineering and Information Technology (pp. 196-210). Springer, Berlin, Heidelberg.
  10. Cho, S. H., Nam, H. S., Ryu, K. J., & Ryoo, D. K. (2020). A Comparative Analysis of the Forecasting Performance of Coal and Iron Ore in Gwangyang Port Using Stepwise Regression and Artificial Neural Network Model. Journal of Navigation and Port Research, 44(3), 187-194. https://doi.org/10.5394/KINPR.2020.44.3.187
  11. Choi, S. H., Oh, S. W., & Kim, Y. S. (2014). Development of enforcement rate for occupational safety and health management expense by construction project types and the percentage of completion. Journal of the Architectural Institute of Korea structure & construction, 30(7), 105-114. https://doi.org/10.5659/JAIK_SC.2014.30.7.105
  12. Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 315-323). JMLR Workshop and Conference Proceedings.
  13. Huh, Y, K., Kim, D, Y., & Yoon, S, M. (2017). A Study on the Improvement of Industrial Safety and Health Management Cost in Construction Industry. Korea Occupational Safety & Healthy Agency.
  14. Hyun, C. T., Hong, T. H., Son, M. J., & Jang, D. W. (2009). Development of the construction cost prediction model based on case-based reasoning in the planning phase of mega-project. Journal of the Architecture Institute of Korea, 25(9), 181-190.
  15. Jin, S. K., & Kim, M. R. (2019). A Study on the Reform the Industrial Safety and Health Management System, GRI REVIEW 21(4), 2019.11, 85-106(22 pages)
  16. Kendall, A., & Gal, Y. (2017). What uncertainties do we need in bayesian deep learning for computer vision?. arXiv preprint arXiv:1703.04977.
  17. Kim, J. W. (2012). A Study on Construction Cost Estimation Model of Educational Facilities using Regression Analysis -For the BTL Project in the Gyeonggi-do Region- (Doctoral dissertation, Hanyang University).
  18. Kim, M. R., & Lee, Y. J. (2018). A Study on the Improvement of Industrial Safety and Health Management Expenses in Plant Construction Industry. National Assembly Convergence Innovation Economic Forum Academic Presentation Data Collection.
  19. Kim, Y. C., Yoo, W. S., & Shin, Y. S. (2017). Application of artificial neural networks to prediction of construction safety accidents. Journal of the Korean Society of Hazard Mitigation, 17(1), 7-14. https://doi.org/10.9798/KOSHAM.2017.17.1.7
  20. Ko, S. J., Lee, K. T., Kim, K. H., & Kim, J. H. (2021). Prediction of Compensation Costs in Apartment Housing Defects Lawsuits using Regression Analysis. Journal of Architectural Institute of Korea, 37(2), 197-204. https://doi.org/10.5659/JAIK.2021.37.2.197
  21. Lee, G., Han, C. H., & Lee, J. (2019). The Development of Productivity Prediction Model for Interior Finishes of Apartment using Deep Learning Techniques. Korean Journal of Construction Engineering and Management, 20(2), 3-12. https://doi.org/10.6106/KJCEM.2019.20.2.003
  22. Lee, J. m., Park, S. H., Cho, S. h., & Kim, J. H. (2021), Comparison of Models to Forecast Real Estates Index Introducing Machine Learning. Journal of Architectural Institute of Korea, 37 (1), Proceedings, 191 - 199. https://doi.org/10.5659/JAIK.2021.37.1.191
  23. Lee, M. G., Jeong, M. J., Kim, S. M., & Kim, H. S. (2010). The current status and proplem analysis of the occupational safety and health expenses in construction. In Proceedings of the Safety Management and Science Conference (pp. 299-307). Korea Safety Management and Science.
  24. Lera, G., & Pinzolas, M. (2002). Neighborhood based Levenberg-Marquardt algorithm for neural network training. IEEE transactions on neural networks, 13(5), 1200-1203. https://doi.org/10.1109/TNN.2002.1031951
  25. Ministry of Employment and Labor 2020-63, Industrial Safety and Health Management Cost Estimation and Usage Criteria for Construction Industry
  26. Mishra, S., Prusty, R., & Hota, P. K. (2015). Analysis of Levenberg-Marquardt and Scaled Conjugate gradient training algorithms for artificial neural network based LS and MMSE estimated channel equalizers. In 2015 International Conference on Man and Machine Interfacing (MAMI) (pp. 1-7). IEEE.
  27. Moller, M. F. (1993). A scaled conjugate gradient algorithm for fast supervised learning. Neural networks, 6(4), 525-533. https://doi.org/10.1016/S0893-6080(05)80056-5
  28. Oh, S. W., Kim, C. W., & Seo, J. H. (2018). A Study on the Transparency of Industrial Safety and Health Management Expenses in Construction Industry. Korea Occupational Safety & Healthy Agency.
  29. Oh, S. W., Kim, Y. S., Choi, S. H., & Choi, J. W. (2013). A study on the estimation of occupational safety and health expense rate by safety environment change in construction industry. Korean Journal of Construction Engineering and Management, 14(4), 97-107. https://doi.org/10.6106/KJCEM.2013.14.4.097
  30. Paliwal, M., & Kumar, U. A. (2009). Neural networks and statistical techniques: A review of applications. Expert systems with applications, 36(1), 2-17. https://doi.org/10.1016/j.eswa.2007.10.005
  31. Ryu, J. I. (2017). An analysis of industrial safety and health management costs for small private construction sites considering industrial accident injury. Kyunggi University Graduate School of Construction and Industry
  32. Shin, S. W. (2017). Construction Safety and Health Management Cost Prediction Model using Support Vector Machine. Journal of the Korean Society of Safety, 32(1), 115-120. https://doi.org/10.14346/JKOSOS.2017.32.1.115
  33. Shon, J. S. (2018). Industrial Safety and Health Management Expenses Operation Actual. The Korean Society of Disaster Information. 155-156
  34. Son, K. S., Gal, W. M., & Yang, H. S. (2007). A study on the estimating rate of safety management cost in building work. Journal of the Korean Society of Safety, 22(5), 33-40.
  35. Son, K. S., Gal, W. M., Park, J. K., Yang, H. S., Choi, J. N., Park, J. B., & Kim, S. K. (2005). Establishing appropriate rate for standard safety & health management cost. The Korea Occupational Safety and Health Agency.
  36. Yeom, D. J., Lee, M. Y., Oh, S. W., Han, S. W., & Kim, Y. S. (2015). Development of a Safety and Health Expense Prediction Model in the Construction Industry. Korean Journal of Construction Engineering and Management, 16(6), 63-72. https://doi.org/10.6106/KJCEM.2015.16.6.063
  37. Yoon, S., Bang, H. T., Kim, G. Y., & Jeon, H. (2021). Evaluation of a Thermal Conductivity Prediction Model for Compacted Clay Based on a Machine Learning Method. Journal of The Korean Society of Civil Engineers, 41(2), 123-131.