prikaz prve stranice dokumenta Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar
No public access
master's thesis
Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. urn:nbn:hr:168:514999
Bedeković, Vedran
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Bedeković, V. (2024). Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:514999

Bedeković, Vedran. "Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:514999

Bedeković, Vedran. "Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:514999

Bedeković, V. (2024). 'Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:514999

Bedeković V. Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 December 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:514999

V. Bedeković, "Predviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:514999

Metadata
TitlePredviđanje uspjeha studenata u sustavu za automatsko ocjenjivanje programskog kôda Edgar
Title (english)Predicting student success in Edgar automated programming assessment system
AuthorVedran Bedeković
MentorIgor Mekterović (mentor)
Committee memberIgor Mekterović (predsjednik povjerenstva)
Committee memberLjiljana Brkić (član povjerenstva)
Committee memberBoris Milašinović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-09-16, Croatia
Abstract
Rastom značajnosti online platformi za učenje omogućuje veliki broj upisanih studenata na pojedinim kolegijima, ali zauzvrat nastavnici ne mogu pravovremeno prepoznati studente koji imaju poteškoće s gradivom. Kako se sustav za automatizirano ocjenjivanje programskog kôda Edgar suočava s istim problemom, ovaj rad ulazi u istraživačke radove u području dubinske analize podataka u obrazovanju te se prema njima razvija sustav usporedbe različitih algoritama strojnog učenja za predviđanje uspjeha studenata. Pomoću njega se zaključuje da se najbolja metoda za predviđanje uspjeha razlikuje za pojedini kolegij. Oko tog sustava se gradi zaseban podesivi modul predviđanja uspjeha koji može koristiti bilo koji kolegij koji ujedno koristi Edgar. Modul raspolaže s Judge0 sustavom za izvršavanje treniranja modela, ali ako kolegij sadrži veliki broj upisanih studenata primoran je izvršavati svoj programski kôd lokalno. Konačno se daje pogled u web sučelje koje olakšava nastavnicima upravljanje projektiranim modulom te nudi vizualizacije za prepoznavanje i analizu kritičnih studenata.
Abstract (english)
The growing importance of online learning platforms allows for a lot off enrolled students in certain courses, but in turn, teachers cannot timely recognize students who have difficulties with the learning material. As the automated programming assessment system Edgar faces the same problem, this dissertation delves into research in the field of educational data mining and creates a system for cross validation of different machine learning models for predicting student success. This system concludes that the best method for predicting success varies from course to course. A standalone adjustable success prediction module is built around this system, which can be used by any course that also uses Edgar. The module uses the Judge0 system for executing the training of the model, but if the course contains a large number of enrolled students, it is forced to execute its code locally. Finally, a look at the web interface is provided, which facilitates teachers in managing the designed module and offers visualizations for identifying and analyzing at-risk students.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:514999
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2024-10-12 20:04:59