Development of an Obesity Information Diagnosis Model Reflecting Body Type Information Using 3D Body Information Values

Abstract

This study uses various body values (length, circumference, and volume) that can be derived from 3D data to determine variables and areas that substantially affect obesity and suggests guidelines for diagnosing obesity that are more elaborate than existing obesity indices. Body data for 170 participants (87 men and 73 women aged 20-30 years) are collected for the chest, abdomen, hips, and arms/legs. A 3D scanner, which can produce accurate body point results, and dual-energy X-ray (DEXA), which can accurately determine the fat percentage, are used to derive fat rates for each body part. The fat percentage and total fat percentage for each body part are used as learning data. For the derived data, the eigenvalue for each body part is derived using a principal component analysis, and the following four clusters are created for each part: underweight, normal, overweight, and obese. A comparison with the obesity index, which diagnoses obesity based on the cluster model, showed that the accuracy of the model proposed in this study is higher at 80%. Therefore, this model can determine the body information necessary for accurate obesity diagnosis and be used to diagnose obesity with greater accuracy than obesity indices without a body fat measurement machine such as DEXA.