Muddam, Akanksh Reddy (2024) Personalised Meal Recommendation System for Health and Dietary Optimization: Design and Implementation. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (931kB) | Preview |
Preview |
PDF (Configuration Manual)
Download (213kB) | Preview |
Abstract
This work aims at creating a meal recommendation system with consideration to users’ dietary needs and characteristic /health issues as the demand for healthy eating increases. A two-filter system is used: content-based filtering, based on the list of ingredients of the dishes and meals’ nutritional values, and collaborative filtering based on individual users’ profiles; for which the K-Nearest Neighbors algorithm was adapted with K = 5. Web scraped and preprocessed data sets are used for training as well as testing purposes and a demo data set is also available. The first findings suggest the feasibility of the model as evidenced by its ability to offer appropriate meal suggestions, achieve maximum user satisfaction, and ultimately, encourage users to embrace healthier diets. Thus, the given system is ready for future development, as the improvements can be easily integrated in terms of real-time feedback analysis and dynamic profile updates.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Del Rosal, Victor UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning Q Science > QP Physiology > Nutrition R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine > Personal Health and Hygiene |
Divisions: | School of Computing > Master of Science in Artificial Intelligence |
Depositing User: | Ciara O'Brien |
Date Deposited: | 20 Jun 2025 08:58 |
Last Modified: | 20 Jun 2025 08:58 |
URI: | https://norma.ncirl.ie/id/eprint/7956 |
Actions (login required)
![]() |
View Item |