Deep Learning-Based Body Shape Clustering Analysis Using 3D Body Scanner: Application of Transformer Algorithm
,
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.
2. Myles TJM (1964). Body type and pre-eclamptic toxemia. Am J Obstet Gynecol, 90(8):1324-1331.
3. Orvanová E (1990). Somatotypes of weight lifters. J Sports Sci, 8(2):119-137.
4. Carter AP (1970). Structural change in the American economy. Harvard University Press.
5. Gryko K, Kopiczko A, Mikołajec K, et al (2018). Anthropometric variables and somatotype of young and professional male basketball players. Sports (Basel), 6(1): 9.
6. Sánchez-Muñoz C, Muros JJ, Cañas J, et al (2020). Anthropometric and physical fitness profiles of world-class male padel players. Int J Environ Res Public Health, 17(2):508.
7. Katzmarzyk PT, Leonard WR (1998). Climatic influences on human body size and proportions: ecological adaptations and secular trends. Am J Phys Anthropol, 106(4):483-503.
8. Koleva M, Nacheva A, Boev M (2002). Somatotype and disease prevalence in adults. Rev Environ Health, 17(1):65-84.
9. Lee JY, Lee SY, Park JH, et al (2023). Exploring a 3D Body Images Based Somatotype Prediction Model using Multi-Class Classification Machine Learning. KSME. 25(3):13-28.
10. Fang H, Berg E, Cheng X, et al (2018). How to best assess abdominal obesity. Curr Opin Clin Nutr Metab Care, 21(5):360-365.
11. Giachetti A, Lovato C, Piscitelli F, et al (2015). Robust automatic measurement of 3D scanned models for the human body fat estimation. IEEE J Biomed Health Inform, 19(2):660-667.
12. Tinsley GM, Moore ML, Benavides ML, et al (2020). 3-Dimensional optical scanning for body composition assessment: A 4-component model comparison of four commercially available scanners. Clin Nutr, 39(10):3160-3167.
13. Jeon S, Kim M, Yoon J, et al (2023). Machine learning-based obesity classification considering 3D body scanner measurements. Sci Rep, 13(1):3299.
14. Vaswani A, Shazeer N, Parmar N, et al (2017). Attention is all you need. Adv Neural Inf Process Syst, 30.
15. Chiu CY, Ciems R, Thelwell M, et al (2022). Estimating somatotype from a single-camera 3D body scanning system. Eur J Sport Sci, 22(8):1204-1210.
16. Yun HJ, Kim CG, Jeon MS (2023). Classification of World Taekwondo Men’s Match Types Applying Deep Learning: Application of Transformer Algorithm. JKAMA, 25(3):143-154.
17. Li ZY, Sun YJ, Zhang CC, et al (2023). Optimizing hydrogen ad/desorption of Mg-based hydrides for energy-storage applications. J Mater Sci Technol, 141:221-235.
18. Buffa R, Lodde M, Floris G, et al (2007). Somatotype in Alzheimer’s disease. Gerontology, 53(4):200-204.
| Files | ||
| Issue | Vol 54 No 1 (2025) | |
| Section | Original Article(s) | |
| Keywords | ||
| Deep learning 3D body scanner Transformer algorithm Body shape | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
