Thesis supervisor: István Vassányi
Location of studies (in Hungarian): University of Pannonia, H-8200 Veszprém, Egyetem str. 10., Hungary Abbreviation of location of studies: PE
Description of the research topic:
The proper lifestyle, including balanced nutrition, plays a very important role in the management of chronic diseases such as diabetes. For such diseases, the automated generation of meal plans could provide more personalised and concrete support than general dietary advice. The aim of the proposed research is to design, implement and test new meal plan generation methods that can satisfy personalised daily or weekly numerical nutrient targets while also taking into account the professional dietetic requirements for the composition of individual meals as well as the daily or weekly meal plans. The background of the research at the MIRDC is a multi-level, multi-objective genetic algorithm library for the design of weekly meal plans that satisfy numerical constraints on the nutrients [1], and the modelling of expert rules based on food and recipe sets [2]. The research will investigate the quality of the plans produced by the genetic algorithm using harmony rules integrated into its cost function, compared to plans prepared manually by the dietetic expert, and also the performance of the solution compared to the performance and accuracy of other currently proposed methods [3]. Further research will be conducted on the automatic completion of incomplete meal logs and the implementation of a new adaptive (learning) service based on user feedback.
Background references:
1. B. Gaál, I. Vassányi, G. Kozmann. A Novel Artificial Intelligence Method for Weekly Dietary Menu Planning. Methods of Information in Medicine (2005); 44: 655–64.
2. István Vassányi, István Kósa, Balázs Pintér, Balázs Gaál. Personalized Dietary Counseling System Using Harmony Rules in Tele-Care. European Journal of Biomedical Informatics, Volume 10 (2014), Issue 2, pp 17-22.
3. Salloum, G., Tekli, J. Automated and personalized meal plan generation and relevance scoring using a multi-factor adaptation of the transportation problem. Soft Computing, (2022) 26(5), 2561–2585.
Further requirements: Notes: The research must be performed personally in the labs of MIRDC. Applicants should have a good command of English, an interest in the field and in scientific research, and good data processing and algorithmic skills/experience.
Deadline for application: 2023-02-28
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
