DIETARY OBESITY RISK LEVEL CLASSIFICATION FOR HEALTH MONITORING

Abstract

Obesity has become a major global health concern due to unhealthy dietary habits, sedentary
lifestyles, and increasing consumption of high-calorie foods. Early identification of obesity
risk can help individuals adopt healthier lifestyles and prevent serious health complications
such as diabetes, cardiovascular diseases, and hypertension. This project proposes a Deep
Learning-based Food and Nutrition Monitoring System that classifies a person’s dietary
obesity risk level using nutritional and lifestyle data.
The system analyzes various parameters such as daily food intake, calorie consumption,
nutritional composition, physical activity levels, body mass index (BMI), age, and eating
habits to predict the obesity risk category of an individual. A deep learning model is trained
on a structured health and nutrition dataset to learn patterns associated with different obesity
levels. The model classifies individuals into categories such as low risk, moderate risk, and
high obesity risk, enabling early health monitoring.
The proposed system provides an intelligent decision-support tool that can assist users,
healthcare professionals, and nutritionists in monitoring dietary behavior and identifying
potential obesity risks. By leveraging deep learning techniques, the system improves
prediction accuracy and enables automated health assessment. This approach contributes to
personalized health monitoring and preventive healthcare, helping individuals make
informed dietary and lifestyle decisions to reduce obesity-related health risks.