• Dinesh Kumavat
• Prakash Kushwaha
• Harish Dalai

The demand for accurate, real-time nutritional data has driven innovation in automated food analysis. Traditional methods, like manual logging or lab tests, are inefficient for widespread application. This paper introduces a sophisticated food nutrition analysis system, combining deep learning and graph neural networks (GNNs). The system utilizes deep learning for precise food image recognition, enabling accurate identification of food items. Subsequently, GNNs model the complex relationships between nutrients, enhancing the accuracy of nutritional profiling. This hybrid approach significantly improves calorie estimation, achieving a mean absolute error (MAE) of 6.8 kcal. Furthermore, the system demonstrates superior performance in macronutrient profiling, outperforming conventional methods by up to 25%. By integrating visual data with structured nutritional relationships, this system offers a scalable and efficient solution for dietary monitoring. This technology holds promise for personalized health optimization, providing users with instant, reliable nutritional insights. The system's ability to quickly analyze food images and accurately predict nutrient content addresses the limitations of traditional dietary assessment methods. This advancement supports proactive health management and contributes to a more informed approach to nutrition.

: Food Nutrition Analysis, Hybrid Machine Learning, Deep Learning, Graph Neural Networks, Nutritional Profiling, Dietary Monitoring.

"Advanced Food Nutrition Analysis System Using Hybrid Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.g703-g705, March-2025, Available :http://www.jetir.org/papers/JETIR2503685.pdf

"Advanced Food Nutrition Analysis System Using Hybrid Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppg703-g705, March-2025, Available at : http://www.jetir.org/papers/JETIR2503685.pdf