Estimation of body fat percentage using hybrid machine learning algorithms

No Thumbnail Available

Date

2021

Journal Title

Journal ISSN

Volume Title

Publisher

Elsevier Sci Ltd

Research Projects

Organizational Units

Journal Issue

Abstract

Before obesity treatment, body fat percentage (BFP) should be determined. BFP cannot be measured by weighing. The devices developed to produce solutions to this problem are called "Body Analysis Devices". These devices are very costly. Therefore, more practical and cost-effective solutions are needed. This study aims to determine BFP using hybrid machine learning methods with high accuracy rate and minimum parameter. This study uses real data sets, which are 13 anthropometric measurements of individuals. Different feature groups were created with feature selection algorithm. In the next step, 4 different hybrid models were created by using MLFFNN, SVMs, and DT regression models. According to the results, BFP of individuals can be estimated with a correlation value of R = 0.79 with one anthropometric measurement. The results show that the developed system can be used to estimate BFP in practice. Besides, the system can calculate BFP with just one anthropometric measurement without device requirement. (C) 2020 Elsevier Ltd. All rights reserved.

Description

Keywords

Body composition, Body fat percentage calculation, Body fat percentage estimation, Machine learning, Artificial intelligence

Turkish CoHE Thesis Center URL

Citation

19

WoS Q

Q1

Scopus Q

Q1

Source

Volume

167

Issue

Start Page

End Page