Korean Journal of Construction Engineering and Management (한국건설관리학회논문집)

Korea Institute of Construction Engineering and Management (한국건설관리학회)
권호 표지
DOI QR코드

DOI QR Code

An interpretable machine learning approach for forecasting personal heat strain considering the cumulative effect of heat exposure

  • Seo, Seungwon (Department of Architecture, Incheon National University) ;
  • Choi, Yujin (Department of Architecture, Incheon National University) ;
  • Koo, Choongwan (Division of Architecture & Urban Design, Incheon National University)
  • Received : 2023.04.05
  • Accepted : 2023.08.21
  • Published : 2023.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Climate change has resulted in increased frequency and intensity of heat waves, which poses a significant threat to the health and safety of construction workers, particularly those engaged in labor-intensive and heat-stress vulnerable working environments. To address this challenge, this study aimed to propose an interpretable machine learning approach for forecasting personal heat strain by considering the cumulative effect of heat exposure as a situational variable, which has not been taken into account in the existing approach. As a result, the proposed model, which incorporated the cumulative working time along with environmental and personal variables, was found to have superior forecast performance and explanatory power. Specifically, the proposed Multi-Layer Perceptron (MLP) model achieved a Mean Absolute Error (MAE) of 0.034 (℃) and an R-squared of 99.3% (0.933). Feature importance analysis revealed that the cumulative working time, as a situational variable, had the most significant impact on personal heat strain. These findings highlight the importance of systematic management of personal heat strain at construction sites by comprehensively considering the cumulative working time as a situational variable as well as environmental and personal variables. This study provided a valuable contribution to the construction industry by offering a reliable and accurate heat strain forecasting model, enhancing the health and safety of construction workers.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP; Ministry of Science, ICT & Future Planning) (NRF-2020R1C1C1004147).

References

  1. Amari, S. (1967). "A theory of adaptive pattern classifiers. IEEE Transactions on Electronic Computers." 3, pp. 299-307.  https://doi.org/10.1109/PGEC.1967.264666
  2. Agirre-Basurko, E., Ibarra-Berastegi, G., and Madariaga, I. (2006). "Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area." Environmental Modelling & Software, 21(4), pp. 430-446.  https://doi.org/10.1016/j.envsoft.2004.07.008
  3. Breiman, L. (2001). Random forests. Machine learning, 45(1), pp. 5-32.  https://doi.org/10.1023/A:1010933404324
  4. Chen, T., and Guestrin, C. (2016). "XGBoost: A scalable tree boosting system." Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785-794. 
  5. Du, C., Li, B., Li, Y., Xu, M., and Yao, R. (2019). "Modification of the Predicted Heat Strain (PHS) model in predicting human thermal responses for Chinese workers in hot environments." Building and Environment, 165, 106349. 
  6. Drucker, H., Burges, C.J., Kaufman, L., Smola, A., and Vapnik, V. (1996). Support vector regression machines. Advances in neural information processing systems, 9.
  7. Haykin, S., and Lippmann, R. (1994). "Neural networks, a comprehensive foundation." International Journal of Neural Systems, 5(4), pp. 363-364. 
  8. Hastie, T., Tibshirani R., Friedman, J.H., and Friedman, J.H. (2009). "The elements of statistical learning: data mining, inference, and prediction (2nd)." Springer, 2, pp. 1-758. 
  9. ISO 7243 (1989). "Hot Environments-Estimation of the heat stress on working man, based on the WBGT-index (wet bulb globe temperature)" International Standrds Organization, Geneva. 
  10. ISO 7933 (2004). "Ergonomics of the thermal environment analytical determination an interpretation of heat stress using calculation of the predicted heat strain." International Standardization Organization, Geneva. 
  11. ISO 8996:2004. (2004). Ergonomics of the thermal environment - Determination of metabolic rate. International Organization for Standardization (ISO). 
  12. Ilager, S., Ramamohanarao, K., and Buyya, R. (2020). "Thermal prediction for efficient energy management of clouds using machine learning." IEEE Transactions on Parallel and Distributed Systems, 32(5), pp. 1044-1056. 
  13. Korea Meteorological Administration (KMA) (2020). Korean Climate Change Assessment Report 2020. KMA. 
  14. Korea Occupational Safety and Health Agency (KOSHA) (2017). Guidelines for Managing High-Temperature Work Environment. KOSHA. 
  15. Korea Occupational Safety and Health Agency (KOSHA) (2018). Guideline for Health Protection for Outdoor Workers (Heatwave). KOSHA. 
  16. Li, S. (2019). "Prediction of body temperature from smart pillow by machine learning." 2019 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 421-426. 
  17. Lundgren-Kownacki, K., Martinez, N., Johansson, B., Psikuta, A., Annaheim, S., and Kuklane, K. (2017). "Human responses in heat-comparison of the Predicted Heat Strain and the Fiala multi-node model for a case of intermittent work." Journal of thermal biology, 70, pp. 45-52.  https://doi.org/10.1016/j.jtherbio.2017.05.006
  18. Ministry of Employment and Labor (MOEL) (2023). Guideline for the Three Basic Rules (Water, Shade, and Rest) against Heatwaves in the Workplace. [online] Available at: http://www.moel.go.kr/news/enews/report/enewsView.do? news_seq=12311 (accessed February 16, 2023), MOEL. 
  19. Rastogi, S.K., Gupta, B.N., Mathur, N., and Husain, T. (1989). "Thermal stress and physiological strain of children exposed to hot environments in a glass bangle factory." European journal of applied physiology and occupational physiology, 59, pp. 290-295.  https://doi.org/10.1007/BF02388331
  20. Rinanto, N., and Kuo, C.H. (2021). "PCA-ANN Contactless Multimodality Sensors for Body Temperature Estimation." IEEE Transactions on Instrumentation and Measurement, 70, pp. 1-16.  https://doi.org/10.1109/TIM.2021.3112778
  21. Shourav, M.K., Salsabila, S., Lee, J.Y., and Kim, J.K. (2021). "Estimation of core body temperature by near-infrared imaging of vein diameter change in the dorsal hand." Biomedical Optics Express, 12(8), pp. 4700-4712.  https://doi.org/10.1364/BOE.431534
  22. World Health Organization (WHO) (1969). Health Factors Involved in Working under Conditions of Heat Stress, WHO Publications. 
  23. Zare, S., Shirvan, H.E., Hemmatjo, R., Nadri, F., Jahani, Y., Jamshidzadeh, K., and Paydar, P. (2019). "A comparison of the correlation between heat stress indices (UTCI, WBGT, WBDT, TSI) and physiological parameters of workers in Iran." Weather and Climate Extremes, 26, 100213.