Deep Learning-Based Body Shape Clustering Analysis Using 3D Body Scanner: Application of Transformer Algorithm

Minsoo  Jeon; Jiwun  Yoon; Hyo Jun  Yun

doi:10.18502/ijph.v54i1.17583

Minsoo Jeon Department of International Sport, Dankook University, Chungcheongnam-do, Republic of Korea
Jiwun Yoon Center for Sports Performance Analytics, Korea National Sport University, Seoul, Republic of Korea
Hyo Jun Yun Center for Sports Performance Analytics, Korea National Sport University, Seoul, Republic of Korea

DOI: https://doi.org/10.18502/ijph.v54i1.17583

Keywords: Deep learning; 3D body scanner; Transformer algorithm; Body shape

Abstract

Background: This study was conducted to perform deep learning-based body shape cluster analysis using 3D Body Scanner.

Methods: For this study, 54 variables were measured using 3D Body Scanner on 366 adult men and women at Korea National Sport University in 2022. Transformer learning and dimensionality reduction models were used to perform cluster analysis on the measured data. Mann-Whitney test and Kruskal-Wallis test were applied to compare the principal component differences of new scale characteristics, and all statistical significance levels were set at .05.

Results: First, among the two methods for classifying body types, the transformer algorithm had a higher performance in body type classification. Second, in the classification of body type clusters, two clusters, endomorphic body type and ectomorphic body type, were divided into six clusters, two for cluster 1 and four for cluster 2.

Conclusion: The six clusters provide more granular information than previous body type classifications, and we believe that they can be used as basic information for predicting health and disease.