:: Volume 25, Issue 4 (11-2017) ::
sjimu 2017, 25(4): 171-178 Back to browse issues page
Stimated Body Fat Percentage using Mechine Learning Techniques
Rasmiyeh Asgari1, Mohammad Reza Valizadeh 2, Korosh Jafariyan3
1- Dept of Computer, Islamic Azad University, Ilam Branch, Ilam, Iran
2- Dept of Computer, Faculty of Engineering, Ilam University, Ilam, Iran , valizadehmr@gmail.com
3- Dept of Nutrition, Faculty of Nutrition and Dietetics, Tehran University of Medical Sciences, Tehran, Iran
Abstract:   (2770 Views)

 Introduction: Doctors undertake calculation of body fat percentage by using BIA (Bioelectrical Impedance Analysis) equipment. In this study, we measured body fat percentage without using equipment. For this purpose, an artificial neural network has been used to estimate the exact amount of fat.
 
Materials & methods: The sample was selected from patients admitted in a nutrition clinic in Tehran. 400 patients took part in this study. MLP neural network was used to estimate body fat percentage. The used neural network had five input neurons and ten neurons in the hidden layer. Also, cross validation method for evaluating the proposed method has been used.
 
Findings: The proposed method is efficient because of the results that demonstrate 2.5 units error based on cross validation. The results of experiments show that the proposed neural network for estimating body fat percentages has an average accuracy of 93%. Therefore the proposed method can accurately estimate body fat percentage of people with very high accuracy.
 
Discussion & conclusions: The results of this research show that the proposed method as the first method used in machine learning technique, can estimate fat percentage with high accuracy. This method can be used as a useful method without using BIA device.
 
 

Keywords: Learning algorithm, Body fat percentage, Data mining, Neural network
Full-Text [PDF 572 kb]   (1448 Downloads)    
Type of Study: Applicable |
Received: 2016/08/30 | Accepted: 2017/03/5 | Published: 2017/12/2



XML   Persian Abstract   Print



Volume 25, Issue 4 (11-2017) Back to browse issues page