Transparent Nutrition: An Explainable AI-based Diet Tracking System for Preventing Nutrition-Related Disorders

Guardado en:

Detalles Bibliográficos
Publicado en:	The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 1798-1803
Autor principal:	Sanitha, P C
Otros Autores:	Parveen, Syed Nageena, Shaik Thaherbasha, Shanmugapriya, M, Kalaivani, T, Senthilkumar, R
Publicado:	The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Materias:	Anemia Internet of Things Diet Food Iron Cardiovascular diseases Tracking systems Nutrition Machine learning Explainable artificial intelligence Nutrient content Nutrients Cyber-physical systems Diabetes mellitus Nutrient status Deep learning Real time Health risks Social
Acceso en línea:	Citation/Abstract
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Descripción
Resumen:	Conference Title: 2025 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI)Conference Start Date: 2025 Sept. 17Conference End Date: 2025 Sept. 19Conference Location: Coimbatore, IndiaThe growing incidence of nutrition-related diseases, including obesity, diabetes mellitus, iron-deficiency anemia, and cardiovascular disease, calls for an accurate, personalized, and transparent dietary monitoring tool. Where past diet tracking apps are the product of user input or general food data, they often fall short of providing the requisite intelligence or explainability to accurately assess nutrient content and health high-risk status. Herein we present an Explainable AI (XAI) based diet tracking system that uses deep learning for automated food recognition, and machine learning for and nutrient estimation and interpretable models to assess the health risks of potential dietary imbalances. Given a food image, the system identifies consumed food items, measures key nutrients (such as calories, sugar, and iron) and identifies an imbalance in nutrient consumption that may cause or worsen nutrition-related disease. To enhance trust and transparency, we use SHapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to showcase how much each piece of dietary information contributed to nutrient limits and health predictions. Results from experiments on the Food-101 dataset and nutrition databases demonstrate our system’s ability to deliver reliable, real-time, and explainable dietary feedback, leveraging XAI for meaningful preventive health taking into consideration user and clinician health implications.
DOI:	10.1109/ICoICI65217.2025.11252549
Fuente:	Science Database