Computational Models for Nutritional Diagnosis and food recognition: A systematic review (#2205)

Authors

Bernal-Saavedra, Leonardo Adriel

Quiroz-Guevara, Johannes

Dios-Castillo, Christian Abraham

Abstract

This study evaluates the effectiveness of computational models in improving nutritional diagnosis and food recognition through the analysis of image-based and numerical data. The research focuses on the performance of Deep Learning (DL), Machine Learning (ML), and hybrid DL + ML approaches, highlighting their role in nutritional evaluation, quality classification, and food identification. Results show that CNN – Based DL models achieve the highest accuracy when processing large and complex datasets, outperforming others architectures in tasks such as nutrient estimation, food quality assessment, and disease detection in crops and food products. Hybrid Ensemble – CNN models demonstrate superior robustness, offering more stable results and enhanced diagnostic performance across multiple applications.