Improving Online Exam Verification with Class-Weighted and Augmented CNN Models
Abstract
The COVID-19 pandemic has shifted interactions to virtual platforms, significantly impacting education, particularly online exams. However, these online exams have vulnerabilities, including exam jockeys. This study proposes a face classification model using a Convolutional Neural Network (CNN) to verify online exam takers. The model uses preprocessing techniques, i.e. normalization, data augmentation, and class weighting, to balance data and enhance generalization utilizing TensorFlow. The results show an overall accuracy of 85%, with a precision of 86.34%, a recall of 84.24%, an F1-score of 85.28% for legal takers, and a precision of 83.65%, recall of 85.81%, and an F1-score of 84.71% for illegal takers. These results indicate the model's balanced performance between legal and illegal classes. By integrating CNN with tailored preprocessing and training strategies, this study addresses gaps in existing authentication methods, offering a robust approach to online exam verification. The proposed model shows a chance for practical applications. However, further optimization through larger datasets and advanced augmentation techniques is recommended to improve its accuracy and adaptability to diverse real-world contexts
The Authors submitting a manuscript do so on the understanding that if accepted for publication, copyright of the article shall be assigned to Jurnal Teknologi Informasi dan Terapan (J-TIT) and Department of Information Technology, Politeknik Negeri Jember as publisher of the journal. Copyright encompasses rights to reproduce and deliver the article in all form and media, including reprints, photographs, microfilms, and any other similar reproductions, as well as translations. Authors should sign a copyright transfer agreement when they have approved the final proofs sent by Jurnal Teknologi Informasi dan Terapan (J-TIT) prior to the publication. The copyright transfer agreement can be download here .
Jurnal Teknologi Informasi dan Terapan (J-TIT) and Department of Information Technology, Politeknik Negeri Jember and the Editors make every effort to ensure that no wrong or misleading data, opinions or statements be published in the journal. In any way, the contents of the articles and advertisements published in Jurnal Teknologi Informasi dan Terapan (J-TIT) are the sole responsibility of their respective authors and advertisers.
Users of this website will be licensed to use materials from this website following the Creative Commons Attribution 4.0 International License. No fees charged. Please use the materials accordingly.
This work is licensed under a Creative Commons Attribution-Share A like 4.0 International License
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
