Automated Reading Detection in an Online Exam
DOI:
https://doi.org/10.3991/ijet.v17i22.33277Keywords:
exam proctoring, reading detection, video recognition, computer vision, deep learningAbstract
In this article, we study the deep learning-based reading detection problem in an online exam proctoring. Pandemia-related restrictions and lockdowns led many educational institutions to go to online learning environments. It brought the exam integrity challenge to an online test-taking process. While various commercial exam proctoring solutions were developed, the online proctoring challenge is far from being fully addressed. This article is devoted to making a contribution to the exam proctoring system by proposing an automated test-taker reading detection method. To this end, we obtain our own dataset of short video clips that resemble a real online examination environment and different video augmentation methods utilized to increase the training dataset. Two different deep learning techniques are adapted for training. The experiments show quite satisfactory results with model accuracy varying from 98.46% to 100%. The findings of the article can help educational institutions to improve their online exam proctoring solutions, especially in language speaking tests.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Bakhitzhan Kadyrov, Shirali Kadyrov, Alfira Makhmutova
This work is licensed under a Creative Commons Attribution 4.0 International License.
The submitting author warrants that the submission is original and that she/he is the author of the submission together with the named co-authors; to the extend the submission incorporates text passages, figures, data or other material from the work of others, the submitting author has obtained any necessary permission.
Articles in this journal are published under the Creative Commons Attribution Licence (CC-BY What does this mean?). This is to get more legal certainty about what readers can do with published articles, and thus a wider dissemination and archiving, which in turn makes publishing with this journal more valuable for you, the authors.
By submitting an article the author grants to this journal the non-exclusive right to publish it. The author retains the copyright and the publishing rights for his article without any restrictions.