{"title":"基于深度学习的三维人体扫描仪体型聚类分析：变压器算法的应用。","authors":"Minsoo Jeon, Jiwun Yoon, Hyo Jun Yun","doi":"10.18502/ijph.v54i1.17583","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>This study was conducted to perform deep learning-based body shape cluster analysis using 3D Body Scanner.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusion: </strong>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.</p>","PeriodicalId":49173,"journal":{"name":"Iranian Journal of Public Health","volume":"54 1","pages":"133-143"},"PeriodicalIF":1.6000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787839/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep Learning-Based Body Shape Clustering Analysis Using 3D Body Scanner: Application of Transformer Algorithm.\",\"authors\":\"Minsoo Jeon, Jiwun Yoon, Hyo Jun Yun\",\"doi\":\"10.18502/ijph.v54i1.17583\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>This study was conducted to perform deep learning-based body shape cluster analysis using 3D Body Scanner.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusion: </strong>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.</p>\",\"PeriodicalId\":49173,\"journal\":{\"name\":\"Iranian Journal of Public Health\",\"volume\":\"54 1\",\"pages\":\"133-143\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2025-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787839/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iranian Journal of Public Health\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.18502/ijph.v54i1.17583\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iranian Journal of Public Health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.18502/ijph.v54i1.17583","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH","Score":null,"Total":0}
Deep Learning-Based Body Shape Clustering Analysis Using 3D Body Scanner: Application of Transformer Algorithm.
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.
期刊介绍：
Iranian Journal of Public Health has been continuously published since 1971, as the only Journal in all health domains, with wide distribution (including WHO in Geneva and Cairo) in two languages (English and Persian). From 2001 issue, the Journal is published only in English language. During the last 41 years more than 2000 scientific research papers, results of health activities, surveys and services, have been published in this Journal. To meet the increasing demand of respected researchers, as of January 2012, the Journal is published monthly. I wish this will assist to promote the level of global knowledge. The main topics that the Journal would welcome are: Bioethics, Disaster and Health, Entomology, Epidemiology, Health and Environment, Health Economics, Health Services, Immunology, Medical Genetics, Mental Health, Microbiology, Nutrition and Food Safety, Occupational Health, Oral Health. We would be very delighted to receive your Original papers, Review Articles, Short communications, Case reports and Scientific Letters to the Editor on the above mentioned research areas.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
