Diabetes Diet Recommendation Using Data Sampling and Monitoring System

Abstract

Diabetes is a chronic disease demanding rigorous diet control and frequent blood sugar monitoring. Intelligent dietary assistance systems are becoming increasingly relevant in a growing global diabetic population. This paper proposes an AI based diet suggestion and sugar monitoring system for diabetics. Based on a well organized food database, the system automatically suggests daily diet schedules comprising breakfast, lunch, dinner, and snacks. Every meal is chosen through randomized sampling to cover diversity and nutritional balance. Critical macronutrients calories, proteins, carbohydrates, and fiber are computed on a daily basis and depicted over time to give users actionable information. Users enter their blood sugar values, and the system simultaneously monitors and plots trends of sugar fluctuation. The approach is based on simplicity, accessibility, and real time feedback that is not dependent on advanced machine learning models, making it applicable for personal or clinical practice. Experimental findings show the flexibility of the system to sustain caloric levels with adaptability in meal pairings. The model has potential for future incorporation of supervised learning to facilitate more adaptive and personalized diet advice for diabetic treatment.