Kohli, Karan (2023) Neural Network-Based Detection of Disengagement in Virtual Environment. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
After the COVID-19 pandemic, the learning process has changed significantly, shifting from traditional offline classes to virtual environments. This new platform offers flexibility and accessibility to both students and teachers, but it also comes with some major drawbacks. One prominent issue is that students often lose their focus or engagement during online lectures, making it difficult for teachers to monitor each student effectively. Therefore, the need for an automatic engagement detection system in the virtual environment has become apparent. For this research, the FER-2013 dataset was utilized since it contains various facial emotion expressions which help to detect the student disengagement. While existing research has attempted to address this problem using traditional frameworks, the experimented models have not been capable enough to detect disengagement, partly due to data quality issues. Publicly available datasets tend to be biased towards high-engagement levels since they are more frequently used, leading to insufficient data for training generalizable binary or multi-class classifiers. To tackle this challenge, this study proposes using a deep Convolutional Neural Network (DCNN) to detect student engagement and disengagement effectively. The objective of this research is create an architecture which will help to identify the engagement and disengagement with the help of facial emotions. The proposed model has achieved 84.74% accuracy to detect student engagement state. The work created an webcam based architecture help to detect the participate engagement states such as ”Engaged”,”Neutral”, and ”Not Engaged”. This has been done by analysing the various facial emotional to classify the engagement state.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Shahid, Abdul UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision L Education > LC Special aspects / Types of education > E-Learning |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Tamara Malone |
Date Deposited: | 26 Nov 2024 11:54 |
Last Modified: | 26 Nov 2024 11:54 |
URI: | https://norma.ncirl.ie/id/eprint/7199 |
Actions (login required)
View Item |