Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.15243289 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>The educational system is facing a growing problem with the proliferation of exam cheating as a result of<br>new forms of electronic communication and enjoyment. Most students nowadays are too busy worrying<br>about getting a passing grade to put in the time and effort necessary to really prepare for the test. Classical<br>exam surveillance has become outdated as a result of the emergence of multiple cheating strategies. This<br>means that automated cheating case identification using cutting-edge tech is an absolute need. By utilizing<br>deep learning and computer vision techniques to analyze the student's posture in real-time, this research<br>presents an anti-cheating strategy that focuses on behavior analysis. To do this, we employ YOLO-Faciallandmark and media pipe models to extract domain information from video frames at a high level. The<br>next step in predicting cases of cheating is to employ a decision tree classification model. </p>