The week's pick
Reseach Article
Identification of Classroom Sheet Exam Cheating Trials using a Deep Learning Approach
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 20 |
| Year of Publication: 2024 |
| Authors: Getasew Abeba, Amare Genetu, Sefinew Getenet, Dires Bitew, Fasil Alemu |
10.5120/ijca2024923622
|
Getasew Abeba, Amare Genetu, Sefinew Getenet, Dires Bitew, Fasil Alemu . Identification of Classroom Sheet Exam Cheating Trials using a Deep Learning Approach. International Journal of Computer Applications. 186, 20 ( May 2024), 25-29. DOI=10.5120/ijca2024923622
Abstract
When a student tries to obtain academic credit in a dishonest, discourteous, careless, unreliable, or unjust manner, that behavior is called cheating. It has a variety of effects on the nation, education, as well as the student themselves. One is that cheating causes schooling to become less effective. There are various ways that researchers try to spot exam cheating, but they focus much of their efforts on finding instances of online exam cheating. However, little research has been done on the issue of classroom paper exams. In order to categorize a given classroom exam image as cheating or not, we model the detection of cheating trials as a classification task in this article. The model includes fundamental elements including image preprocessing, image classification, and evaluation approaches to identify cheating trial images. Following many experimental analyses, CNN exhibits the best accuracy of 92% for images with a size of 300 by 300. Finally, we advise considering this research to be a major issue that necessitates an in-depth investigation of dataset preparation. Therefore, we advise researchers to collect cheating trial datasets from various perspectives on cheating cases in order to enhance the model performance.
References
- M. A. Med, “Written Exam Cheating and Prevention and Detection Strategies: The Case Of DMU,” J. Educ. Pract., vol. 10, no. 7, pp. 60–70, 2019, doi: 10.7176/jep/10-7-07.
- J.-A. Hernándeza, A. Ochoab, J. Muñozd, and G. Burlaka, “Detecting cheats in online student assessments using Data Mining,” Conf. Data Mining| DMIN, vol. 6, no. January, p. 205, 2006, [Online]. Available: https://www.researchgate.net/publication/220705005
- F. K. Chiang, D. Zhu, and W. Yu, “A systematic review of academic dishonesty in online learning environments,” J. Comput. Assist. Learn., vol. 38, no. 4, pp. 907–928, 2022, doi: 10.1111/jcal.12656.
- F. Kamalov, H. Sulieman, and D. S. Calonge, “Machine learning based approach to exam cheating detection,” PLoS One, vol. 16, no. 8 August, pp. 1–15, 2021, doi: 10.1371/journal.pone.0254340.
- E. R. Cavalcanti, C. E. Pires, E. P. Cavalcanti, and V. F. Pires, “Detection and evaluation of cheating on college exams using supervised classification,” Informatics Educ., vol. 11, no. 2, pp. 169–190, 2012, doi: 10.15388/infedu.2012.09.
- P. Sharma, U. Tripathi, and U. Kumar, “AUTOMATING ONLINE PROCTORING THROUGH ARTIFICIAL INTELLIGENCE,” pp. 1894–1896, 2021.
- N. Williams, “Non-Representational Theory Non-Representational Theo- ry / Non-Representational Geographies,” 2020.
- D. Jaswal, S. V, and K. P. Soman, “Image Classification Using Convolutional Neural Networks,” Int. J. Sci. Eng. Res., vol. 5, no. 6, pp. 1661–1668, 2014, doi: 10.14299/ijser.2014.06.002.
- G. H. Yun, S. J. Oh, and S. C. Shin, “Image preprocessing method in radiographic inspection for automatic detection of ship welding defects,” Appl. Sci., vol. 12, no. 1, 2022, doi: 10.3390/app12010123.
- A. C. Frery, “Image filtering,” Digit. Doc. Anal. Process., pp. 55–70, 2013, doi: 10.1201/b10797-8.
- E. Bochinski, T. Senst, and T. Sikora, “Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms,” Proc. - Int. Conf. Image Process.
- ICIP, vol. 2017-September, no. August 2018, pp. 3924–3928, 2018, doi: 10.1109/ICIP.2017.8297018.
Index Terms
Keywords