Artificial Neural Network Algorithm in Nutritional Assessment: Implication for Machine Learning Prediction in Nutritional Assessments

Oyekunle, David Oyewumi; Esseme, Alain Claude Bah; Oladipupo, Matthew Abiola; Oseni, Victoria Enemona; Adebola, Nabeela Temitayo; Nwaiku, Morgan; Nwanakwaugwu, Andrew Chinonso; Matthew, Ugochukwu Okwudili

Abstract

In the current study, we used an artificial neural network (ANN) machine learning algorithm to construct an artificial intelligence-based nutritional assessment system. The algorithm used information from a user's regular meals as well as their preexisting health indicators to formulate a machine based nutritional assessment requirement. ANN-based nutritional evaluation approaches will make it possible to assess eating habits, recommend daily meals, and improve general health. In particular, we develop a machine learning technique to identify multiple food items by classifying them using an ANN machine algorithm and identifying suitable nutritional assessments using anthropometric, biochemical, clinical, and dietary (ABCD) data. Using an ANN machine learning model, the artificial intelligence system initially creates a number of proposals from the input. Next, using information from the unique ABCD nutritional evaluation, it creates feature maps for each proposal and used the ANN machine learning algorithm to classify diet interval and its composition.

• Publication Date: Sep 20, 2024
• Deposit Date: Jan 31, 2025
• Publisher: IGI Global
• Pages: 253-276
• Book Title: Precision Health in the Digital Age: Harnessing AI for Personalized Care
• Chapter Number: 13
• ISBN: 9798369344224; 9798369344231
• DOI: https://doi.org/10.4018/979-8-3693-4422-4.ch013