PROTEIN H2020 Project

Part of EU Open Research Repository
Published October 21, 2022 | Version v1
Journal article Open

PROTEIN AI Advisor: A Knowledge-Based Recommendation Framework Using Expert-Validated Meals for Healthy Diets

Authors/Creators

  • 1. Information Technologies Institute, Centre for Research and Technology Hellas, GR 57001 Thessaloniki, Greece
  • 2. School of Biosciences and Medicine, Faculty of Health and Medical Sciences, University of Surrey, Guildford GU2 7XH, UK
  • 3. Department of Rehabilitation Sciences, Katholieke Universiteit Leuven, 3001 Leuven, Belgium
  • 4. Department of Endocrinology, Diabetes and Nutrition, Charité, 10117 Berlin, Germany
  • 5. Department of Nutritional Sciences and Dietetics, International Hellenic University, GR 57400 Thessaloniki, Greece
  • 6. Institute of Applied Biosciences, Centre for Research and Technology Hellas, GR 57001 Thessaloniki, Greece
  • 7. Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki, GR 54124 Thessaloniki, Greece
  • 8. Centro Interdisciplinar de Estudo da Performance Humana (CIPER), Universidade de Lisboa, Estrada da Costa, Dafundo, 1499-002 Lisbon, Portugal
  • 9. PLUX, Wireless Biosignals, 1050-059 Lisbon, Portugal
  • 10. Intrasoft International SA, 1253 Luxembourg, Luxembourg

Description

AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system’s effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations.

Files

PROTEIN_AI_Advisor.pdf

Files (1.0 MB)

Name Size Download all
md5:54919faff44ba85b2f3c81ce4d25820c
1.0 MB Preview Download

Additional details

Related works

Is supplement to
Dataset: 10.5281/zenodo.7143233 (DOI)

Funding

European Commission
PROTEIN - PeRsOnalized nutriTion for hEalthy livINg 817732