Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.12188/17559
Title: Неуро-фази моделирање на адаптивен видеоконференциски систем за далечинско учење
Other Titles: Neuro-fuzzy modeling of adaptive videoconferencing distance learning system
Authors: Василева Стојановска, Татјана
Keywords: quality of experience, quality of service, blended learning, neuro-fuzzy computing, linear regression, educational outcomes
Issue Date: 2015
Publisher: ФИНКИ, УКИМ, Скопје
Source: Василева Стојановска, Татјана (2015). Неуро-фази моделирање на адаптивен видеоконференциски систем за далечинско учење. Доктроска дисертација. Скопје: ФИНКИ, УКИМ.
Abstract: The modern research appoaches on educational models express tendency for gradual shift from the traditional teacher-centered pedagogies towards models that place the student in the center of the learning proces. The later aproaches aim to create educational environments where students acquire knowledge through direct experience with the educational activities, therefore developing creativity, active research, originality, cooperativity and team work for problem solving. This approach leads to enhanced motivation, persistence and dedication of the students involved in the educational activities. These qualities are needed to acheive success and retain the student in the educational process. Open and distance learning is a flexible aproach that brings the educational process closer to the students, exceeding the space time limitations of the regular formal education and offering open and flexible approach to the educational content to a broader structure of educational consumers. These open systems evolve in time towards the modern student-centered systems integrated in the regular education. The blended educational programs appeared lately, offering educational programs partly implemented as a traditional formal setup and partly employing open online systems. These systems aim to respond to the educational needs of broader class of students and improve the individual experience of the student with the educational process. The percepted sattisfaction during the interaction with the system is a valuable component that influences the overall acceptance of the educational system and the overal success of the system. Subjective perception of the educational process supported with a technology or product quantifies a measure known as "Quality of Experience" defined as a measure of the subjective user perception on the overall system acceptance. This thesis makes an attempt to identify the subjective and objective factors influencing the Quality of Experience. The objective factors arise from the effects of the system on the user's perception, classified as Network and Application Quality of Service. The subjective factors concern the user's expectations, perception and experience with the system. The majority of the research known in the literature, approach the Quality of Experience through its corelation to the objective factors consisting the Quality of Service. In this thesis the Quality of Experience is investigated regarding both objective and subjective factors including personality traits and learning style that are considered to have impact on the perceived Quality of Experience. Having identified the input factors of both subjective and objective nature, a neuro-fuzzy model for Quality of Experience is proposed and developped using the ANFIS soft technique for system identification from the set of input/output data available. The model performances are validated using the standard statistical measures RMSE, MAPE and R2. The obtained results are competitive with the results previously reported in the literature. The research in this thesis goes further to explore the effect of the student perception and the subjective factors including learning style and personality traits on educational outcomes. Besides the construction of the ANFIS models to predict the academic performance and the transferable skills, two complementary statistical models utilizing linear regression technique are constructed as well. The comaprison between the soft and statistical models showed that the ANFIS soft techniques outperform the statistical techniques for prediction of educational outcomes. The results from this thesis contribute towards detailed understanding of the constructs determining and affecting the Quality of Experience, as well as the impact of the personality traits and the individual differences on educational outcomes. These conclusions further contribute towards understanding and construction of adaptive educational systems adjustable to the individual preferences of the students for acheiving optimal educational results.
Description: Докторска дисертација одбранета во 2015 година на Факултетот за информатички науки и компјутерско инженерство во Скопје, под менторство на проф. д–р Владимир Трајковиќ.
URI: http://hdl.handle.net/20.500.12188/17559
Appears in Collections:UKIM 01: Dissertations preceding the Doctoral School / Дисертации пред Докторската школа

Files in This Item:
File Description SizeFormat 
TatjanaVasilevaStojanovska2015.pdf1.87 MBAdobe PDFView/Open
Show full item record

Page view(s)

11
checked on Jul 18, 2024

Download(s)

18
checked on Jul 18, 2024

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.