Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.

E-assessment Malpractice Image classification is very important in education applications to develop an effeactive studies. In this paper, we use imagenet benchmark dataset to classify five types of examination taking and malpractices involved (a) cheat from text books/notes/papers. (b) Using a phone to call. (c) asking a friend in the test room (d) operating a phone and (e) a normal exam taking without cheating. Due to the small number of training dataset, our classification systems evaluate deep transfer learning for feature extraction. . During these exams it is difficult to keep track of every student’s screen at the same time to check if anyone is showing fraudulent behaviour. Even when recording all students’ activities during exam and watching it afterwards to depend if they cheated is very labour intensive. This thesis uses a special type of Convolutional neural network called Inception which is are widely known for their effectiveness in image classification on students’ proctored video recordings to determine if they show any malpractice behaviors, allowing us to build a framework to automate this labour intensive process system. The objective of this study is to increase the classification accuracy, speed the training time and avoid the overfitting. In this study, we trained our architecture to involve minimal pre-processing for 30-epoch number in order to study its impact on classification performance and consuming time. In addition, the paper benefits acceptable results with small number of epoch in limited time. Our interpretations confirm that transfer learning provides reliable results in the case of small dataset. The proposed system outperforms the state-of-the-art methods and achieve 96.8% classification accuracy.

Convolutional Neural Network, Exam Malpractice, Classification, Deep learning, E-assessment, Transfer learning.

1. Adeyemi, J., Ogunlere, S., & Akwaronwu, B. (2025). Real-Time Detection of Examination Malpractices Using Convolutional Neural Networks and Video Surveillance: A Systematic Review with Meta-Analysis. British Journal of Computer, Networking and Information Technology, 8, 15–50. Retrieved from https://doi.org/10.52589/BJCNIT-QC5EELJE. [Google Scholar] [Crossref]

2. Al-Mutairi, A., & Al-Sahli, R. (2024). Secure Authentication System Based on Multi-Factor Authentication. Social Science Research Network (SSRN). Retrieved from https://doi.org/10.13140/RG.2.2.24880.74247. [Google Scholar] [Crossref]

3. Ghosh, S., Das, N., & Nasipuri, M. (2019). Reshaping Inputs for Convolutional Neural Networks—Some Common and Uncommon Methods. Pattern Recognition, 93, 332–348. Retrieved from https://doi.org/10.1016/j.patcog.2019.04.009. [Google Scholar] [Crossref]

4. Hussain, M., Qureshi, Z., & Malik, S. (2024). The Impact of Educational Technologies on Modern Education: Navigating Opportunities and Challenges. Global Educational Studies Review, IX(3), 21–30. Retrieved from https://doi.org/10.31703/gesr.2024(IX-III).03. [Google Scholar] [Crossref]

5. Jantos, A. (2021). Motives for Cheating in Summative E-Assessment in Higher Education - A Quantitative Analysis. In J. Zaharia & M. Deac (Eds.), Proceedings of the 13th International Conference on Education and New Learning Technologies (pp. 1764-1770). IATED. Retrieved from https://doi.org/10.21125/edulearn.2021.1764. [Google Scholar] [Crossref]

6. Karim, Z., & van Zyl, T. L. (2021). Deep/Transfer Learning with Feature Space Ensemble Networks (FeatSpaceEnsNets) and Average Ensemble Networks (AvgEnsNets) for Change Detection Using DInSAR Sentinel-1 and Optical Sentinel-2 Satellite Data Fusion. Remote Sensing, 13(21), 4394. Retrieved from https://doi.org/10.3390/rs13214394. [Google Scholar] [Crossref]

7. Mortezapour Shiri, F., Perumal, T., & Mohamed, R. (2024). A Comprehensive Overview and Comparative Analysis on Deep Learning Model. Journal on Artificial Intelligence, 6(5), 301–360. Retrieved from https://doi.org/10.32604/jai.2024.054314. [Google Scholar] [Crossref]

8. Rawat, W., & Wang, Z. (2017). Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review. Neural Computation, 29, 2352–2449. Retrieved from https://doi.org/10.1162/NECO_a_00990. [Google Scholar] [Crossref]

9. Ribani, R., & Marengoni, M. (2019). A Survey of Transfer Learning for Convolutional Neural Networks. In C. C. Mariotti, M. F. Ortega, L. C. Quaresma, & L. A. Raimundo (Eds.), Proceedings - SIBGRAPI 2019 - XXIV Brazilian Symposium on Graphics and Image Processing (pp. 47-57). São Paulo, Brazil: IEEE. Retrieved from https://doi.org/10.1109/SIBGRAPI-T.2019.00010. [Google Scholar] [Crossref]

10. Sukumaran, A., & Manoharan, A. (2024). Multimodal Engagement Recognition From Image Traits Using Deep Learning Techniques. IEEE Access, PP(1), 1–1. Retrieved from https://doi.org/10.1109/ACCESS.2024.3353053. [Google Scholar] [Crossref]

11. Taherdoost, H. (2023). Deep Learning and Neural Networks: Decision-Making Implications. Symmetry, 15(9), 1723. Retrieved from https://doi.org/10.3390/sym15091723. [Google Scholar] [Crossref]

12. Yulita, I. N., Hariz, F. A., Suryana, I., & Prabuwono, A. S. (2023). Educational Innovation Faced with COVID-19: Deep Learning for Online Exam Cheating Detection. Education Sciences, 13(2), 194. Retrieved from https://doi.org/10.3390/educsci13020194. [Google Scholar] [Crossref]

13. Zhu, W., Braun, B., Chiang, L., & Romagnoli, J. (2021). Investigation of Transfer Learning for Image Classification and Impact on Training Sample Size. Chemometrics and Intelligent Laboratory Systems, 211, 104269. Retrieved from https://doi.org/10.1016/j.chemolab.2021.104269. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet
• Real-Time Traffic Signal Optimisation Using Deep Q-Network Algorithm and Camera Data