A FUZZY LOGIC MODEL FOR ASSESSING OBESITY RISK LEVELS AMONG UNIVERSITY STUDENTS

Abstract

The global prevalence of obesity remains high, with statistics showing that in 2022, one in eight individuals worldwide were living with obesity. Obesity is associated with various health risks, including diabetes, hypertension, sleep apnea, and mental and emotional issues. Addressing obesity during adolescence is crucial for preventing related health problems in adulthood. Consequently, this study focuses on early obesity risk screening among university students using a Fuzzy Logic Model. Key input factors such as Body Mass Index (BMI), parental history, exercise habits, fibre intake, and fast-food consumption were collected from 30 students at UiTM Perlis Branch. The data were analyzed using 162 IF-THEN rules to classify obesity risk into low, medium, and high categories, demonstrating the flexibility and accuracy of fuzzy logic in handling vagueness and uncertainty in health assessments. The survey results indicated that 97% of the respondents were categorized as having a "medium" obesity risk, though at varying degrees within that category. Some students with healthy BMI values still fell into this category due to sedentary lifestyles and frequent consumption of fast food. This study successfully develops and implements a fuzzy logic model to evaluate risk levels of developing obesity. This model could aid the public and healthcare professionals in early diagnosis of obesity risk and could be further enhanced by incorporating additional obesity-related input factors.