| Title |
Clustering-based Model for Identifying Individual Differences in Vulnerability to Heat Strain |
| Authors |
최유진(Choi, Yujin) ; 서승원(Seo, Seungwon) ; 구충완(Koo, Choongwan) |
| DOI |
https://doi.org/10.5659/JAIK.2023.39.3.259 |
| Keywords |
Heat strain; Personal biometric characteristics; Vulnerable group; k-means clustering; Independent samples t-test |
| Abstract |
As the frequency of heat waves rises, it is necessary to manage individual heat strains systematically. To address this challenge, this study
aims to develop a clustering-based model for identifying individual differences in vulnerability to heat strain utilizing two proxy variables:
metabolic rate estimated by heart rate or proxy A and eardrum temperature or proxy B. The k-means clustering method was used to divide
individuals into different groups based on their vulnerability to heat strain and two groups such as high-risk and low-risk were classified for
both of these two proxy variables. An independent samples t-test was used to analyze the differences in the mean values of 13 personal
characteristics between the two groups. As a result, there were significant differences in 11 variables, which were mainly related to body fat
for the groups classified by proxy A, but no significant differences for the groups classified by proxy B. This study is expected to establish
a decision support system that can predict whether a person is at high-risk for heat strain based on their biometric characteristics. |