Εφαρμογή διαιτολογίου με Mamdani Fuzzy Logic

Γκουρνέλος, Χρήστος

Diet plan application using Mamdani Fuzzy Logic

Master Thesis

Author

Γκουρνέλος, Χρήστος

Date

2026-02

Abstract

The main objective of this thesis is to design and implement a web application that produces results by using a Fuzzy Inference System. The algorithm that is being used is the Mamdani Inference Algorithm, with minor modifications. The combination of fuzzy logic and modern web technologies results in a system that is both efficient and provides accurate suggestions. The web application created uses the latest Vue.js framework for the Front End. This results in a modern, responsive, fast, and lightweight web application. The Back End was implemented with Node.js due to its simplicity and seamless integration with the Front End data. More specifically, for the logic of the server the Express framework was used due to its stability, wide use and continuous support. When it comes to architecture, the MVC model was followed since it organizes the codebase well, while also allowing the application to be expanded easily. The data of this application is being handled and stored in a relational MySQL database, chosen for its reliability, simplicity and widespread use. The application creates personalized diet plans for individual users, both authenticated and unauthenticated. To generate these plans, the users are asked to input some personal characteristics and preferences, such as height, weight, dietary habits etc. These inputs are then processed through the Mamdani Fuzzy Inference System to find the most suitable choices for each meal of the day. To avoid repeatability and introduce variety to the generated meal plans, some additional rules were created that influence the final score of a meal. These extra rules coexist with the final Mamdani inference score and affect it by dynamically prioritizing according to previous plans of the user, and the already selected recipes

Postgraduate Studies Programme

Προηγμένα Συστήματα Πληροφορικής - Ανάπτυξη Λογισμικού και Τεχνητής Νοημοσύνης

Department

Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Πληροφορικής

Number of pages

Language

Greek

URI

https://dione.lib.unipi.gr/xmlui/handle/unipi/18971

Collections

Τμήμα Πληροφορικής

Show full item record

Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα