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

다국어 초록 (Multilingual 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.

참고문헌 (Reference)

1 Chen, T., "XGBoost: A scalable tree boosting system" 785-794, 2016

2 Rastogi, S. K., "Thermal stress and physiological strain of children exposed to hot environments in a glass bangle factory" 59 : 290-295, 1989

3 Ilager, S., "Thermal prediction for efficient energy management of clouds using machine learning" 32 (32): 1044-1056, 2020

4 Hastie, T., "The elements of statistical learning: data mining, inference, and prediction, 2" Springer 1-758, 2009

5 Drucker, H., "Support vector regression machines" 9 : 1996

6 Agirre-Basurko, E., "Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area" 21 (21): 430-446, 2006

7 Breiman, L., "Random forests" 45 (45): 5-32, 2001

8 Li, S., "Prediction of body temperature from smart pillow by machine learning" 421-426, 2019

9 Rinanto, N., "PCA-ANN Contactless Multimodality Sensors for Body Temperature Estimation" 70 : 1-16, 2021

10 Haykin, S., "Neural networks, a comprehensive foundation" 5 (5): 363-364, 1994

11 Du, C., "Modification of the Predicted Heat Strain (PHS) model in predicting human thermal responses for Chinese workers in hot environments" 165 : 106349-, 2019

12 Korea Meteorological Administration, "Korean Climate Change Assessment Report 2020" KMA 2020

13 "ISO 8996:2004, Ergonomics of the thermal environment — Determination of metabolic rate"

14 "ISO 7933, Ergonomics of the thermal environment analytical determination an interpretation of heat stress using calculation of the predicted heat strain"

15 ISO 7243, "ISO 7243 , Hot Environments-Estimation of the heat stress on working man, based on the WBGT-index (wet bulb globe temperature)"

16 Lundgren-Kownacki, K., "Human responses in heat–comparison of the Predicted Heat Strain and the Fiala multi-node model for a case of intermittent work" 70 : 45-52, 2017

17 World Health Organization, "Health Factors Involved in Working under Conditions of Heat Stress" WHO Publications 1969

18 Korea Occupational Safety and Health Agency, "Guidelines for Managing High-Temperature Work Environment" KOSHA 2017

19 Ministry of Employment and Labor, "Guideline for the Three Basic Rules (Water, Shade, and Rest) against Heatwaves in the Workplace"

20 Korea Occupational Safety and Health Agency, "Guideline for Health Protection for Outdoor Workers (Heatwave)" KOSHA 2018

21 Shourav, M. K., "Estimation of core body temperature by near-infrared imaging of vein diameter change in the dorsal hand" 12 (12): 4700-4712, 2021

22 Amari, S., "A theory of adaptive pattern classifiers" 3 : 299-307, 1967

23 Zare, S., "A comparison of the correlation between heat stress indices(UTCI, WBGT, WBDT, TSI)and physiological parameters of workers in Iran" 26 : 100213-, 2019