The heat strain of construction workers needs to be managed in advance. In order to develop a real-time heat strain risk classifier that can identify workers who are at high risk for heat strain, metabolic rate estimated by heart rate (proxy A) and ea...
The heat strain of construction workers needs to be managed in advance. In order to develop a real-time heat strain risk classifier that can identify workers who are at high risk for heat strain, metabolic rate estimated by heart rate (proxy A) and eardrum temperature (proxy B) were considered as potential candidates for proxy variables. First, k-means clustering method was used to divide workers based on their level of vulnerability to heat strain; and thus, two groups (i.e., high-risk and low-risk groups) were classified for both of two proxy variables. Second, independent samples t-test was used to analyze the difference between the mean values of 13 personal characteristics from each group. As a result, there were significant differences in 11 variables in the groups classified by proxy A, but no difference in the groups classified by proxy B.