Ocena matematične anksioznosti na podlagi vizualnih signalov

diplomsko delo

Matej Kovač (Author), Andrej Košir (Mentor), Marko Jankovec (Co-mentor)

Abstract

V diplomski nalogi obravnavamo vprašanje do kolikšne mere lahko ocenimo matematično anksioznost na podlagi vizualnih signalov. Poleg opisa krmiljenja kamere za zaznavo skeletnih točk, delo vključuje obdelavo in analizo podatkov, s pomočjo različnih metod strojnega učenja. Zasnova za izvedbo eksperimenta in razpoznave matematične anksioznosti izhaja iz raziskovalnega projekta z naslovom »Spremljanje in izboljšanje individualnih obravnav učencev v COVID in post-COVID razmerah«, ki si prizadeva pomagati osnovnošolskim učencem premagovati anksioznost ob reševanju matematičnih problemov. Pri obdelavi podatkov smo se posluževali različnih razvrščevalnikov strojnega učenja in za izbrane značilke ovrednotili uspešnost posameznih razvrščevalnikov. V našem primeru se je najbolje izkazala metodo podpornih vektorjev. Kljub temu se rezultati uspešnosti razvrščevalnikov niso izkazali za dovolj dobre, da bi zanesljivostjo prepoznavali matematično anksioznost le na podlagi vizualnih signalov.

Keywords

matematična anksioznost;strojno učenje;vizualni signali;kamere za globinsko zaznavo;univerzitetni študij;Elektrotehnika;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2023
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FE - Faculty of Electrical Engineering
Publisher:	[M. Kovač]
UDC:	004:616.89(043.2)
COBISS:	164186115
Views:	16
Downloads:	5
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Assessment of mathematics anxiety based on visual cues
Secondary abstract:	The thesis addresses the question of to what extent we can estimate mathematical anxiety based on visual cues. In addition to programming the camera for detecting skeletal points, the work involves data processing and analysis using various machine learning methods. The design for conducting the experiment and recognizing mathematical anxiety stems from a research project titled "Monitoring and Improving Individual Student Treatments in COVID and Post-COVID Conditions," which aims to assist elementary school students in overcoming anxiety while solving mathematical problems. During the data processing, we employed various machine learning classifiers and evaluated the performance of individual classifiers for the selected features. In our case, the Support Vector method proved to be the most effective. However, the results of the classifier performance did not prove to be sufficiently accurate to reliably identify mathematical anxiety based solely on visual cues.
Secondary keywords:	mathematical anxiety;machine learning;depth-sensing camera;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000313
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za elektrotehniko
Pages:	XIV, 34 str.
ID:	19909020