Comparative Analysis of Predictive Models for Estimating Body Fat Percentage Using Three Models

Yuxuan Qiu

2024

Abstract

Obesity is a common health problem and body fat is an important indicator to measure obesity. However, most methods of measuring body fat require specialized equipment and come at a high cost. Therefore, it is a portable, non-invasive, and cost-effective approach to use a machine learning model to predict body fat. Because existing techniques for measuring body fat have certain challenges and limitations, it is necessary to develop and improve simpler, more economical, and easier methods for measuring body fat. This study will use a body fat prediction dataset from Kaggle to train three different supervised machine learning models: linear regression, decision trees, and support vector machines. Then, the research will compare the performance of three different models through Mean Absolute Error (MAE), Mean Squared Error (MSE), and R square. The evaluation results show that both the linear regression model and the decision tree model have good performance in predicting body fat, while the support vector machine has poor performance in predicting body fat.

Paper Citation

in Harvard Style

Qiu Y. (2024). Comparative Analysis of Predictive Models for Estimating Body Fat Percentage Using Three Models. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 594-598. DOI: 10.5220/0012866600004547

in Bibtex Style

@conference{icdse24,
author={Yuxuan Qiu},
title={Comparative Analysis of Predictive Models for Estimating Body Fat Percentage Using Three Models},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={594-598},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012866600004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Comparative Analysis of Predictive Models for Estimating Body Fat Percentage Using Three Models
SN - 978-989-758-690-3
AU - Qiu Y.
PY - 2024
SP - 594
EP - 598
DO - 10.5220/0012866600004547
PB - SciTePress