Open AccessExamining child obesity risk level using fuzzy inference system
Author(s) -
Febrina Sari,
Desyanti Desyanti,
Teuku Radillah,
Siti Nurjannah,
Julimar Julimar,
Juwita Yanti Pakpahan
Publication year - 2021
Publication title -
international journal of public health science
Language(s) - English
Resource type - Journals
eISSN - 2620-4126
pISSN - 2252-8806
DOI - 10.11591/ijphs.v10i3.20928
Subject(s) - obesity , childhood obesity , fuzzy logic , inference , body mass index , fuzzy inference system , set (abstract data type) , medicine , computer science , statistics , adaptive neuro fuzzy inference system , mathematics , fuzzy control system , artificial intelligence , overweight , programming language
The doctor will determine the risk level of childhood obesity by using standard calculations, namely measuring the child's weight and height, and many other factors. Then the doctor will calculate the child's body mass index (BMI). The results of calculations made by the doctor will be compared with standard/normal values set by FAO/WHO, to obtain the level of risk of obesity in children. This study aims to analyze the risk level of obesity in children using the Sugeno method of Fuzzy Inference system, using the trapezoidal membership function and involving six input variables such as exercise habits, consumption of fast food, history of obesity of parents, and others. The application of the fuzzy inference system Sugeno method can help doctors to analyze the risk level of childhood obesity quickly and accurately with an accuracy rate of 85%. The results of the implementation of the Sugeno method of Fuzzy Inference system showed that out of 140 children who were the object of the study, 119 children received a diagnosis of the level of risk of obesity which was the same as the diagnosis made by a doctor.