Λογισμικό δημιουργίας δυναμικών φύλλων αξιολογήσεων με βάση καθορισμένα από τον χρήστη κριτήρια με την χρήση της ασαφούς λογικής

Μηλιώτη, Αθηνά

Software for creating dynamic evaluation sheets based on user-defined criteria using fuzzy logic

Master Thesis

Author

Μηλιώτη, Αθηνά

Date

2025-11

Abstract

In this thesis, an application is developed that aims to evaluate student performance as well as adjust the difficulty of exercises according to the specific characteristics of each user. The entire application has been implemented with scikit-fuzzy libraries in combination with Flask, where the results and the connection to the MySQL database are displayed through the web application. Our system is divided into two subsystems, the student's fuzzy system and the teacher's fuzzy system. From the student's side, we have data such as the correctness indication, the response time and the difficulty of each exercise. A set of 21 rules is applied, where 18 are for the evaluation and 3 are for the difficulty of the next exercise. Through these rules, the system extracts the performance percentage of each student and with this the proposed difficulty for each exercise is determined. The main purpose of this entire system is to personalize the learning experience for each student. From the teacher's side, we have data such as the percentage of correct answers, the average response time and the average difficulty of exercises. A set of 27 rules is applied to categorize students into categories according to their level. The main purpose of this entire system is to provide the teacher with an image of the students' progress. The results of the system are that it can deal with the uncertainty of each student's performance, adapt to the needs of each student, and provide the teacher with correct information in a simple way. The fuzzy logic applied in our system achieves smooth transitions between categories, avoids the limits of classical models and offers personalized assessment.

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/18520

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