Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams
Online exams are growing increasingly popular in organizations and educational institutes because they are more flexible and cost-effective than conventional paper-based exams. When face-to-face exams are not possible, such as during floods, unexpected situations, or pandemics like COVID-19, this ex...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10416868/ |
| _version_ | 1797311686282051584 |
|---|---|
| author | Muhammad Ramzan Adnan Abid Muhammad Bilal Khalid M. Aamir Sufyan A. Memon Tae-Sun Chung |
| author_facet | Muhammad Ramzan Adnan Abid Muhammad Bilal Khalid M. Aamir Sufyan A. Memon Tae-Sun Chung |
| author_sort | Muhammad Ramzan |
| collection | DOAJ |
| description | Online exams are growing increasingly popular in organizations and educational institutes because they are more flexible and cost-effective than conventional paper-based exams. When face-to-face exams are not possible, such as during floods, unexpected situations, or pandemics like COVID-19, this exam mod has become even more popular and important. However, online exams may have difficulties, such as the need for a reliable internet connection and the possibility of cheating. Because there is no human supervisor present to monitor the exam, so cheating is a major concern. The environment employed for the online exams ensures that every student finalizes the evaluation process without using any type of cheating. This study investigates the detection and recognition of unusual behavior in an academic setting, such as online exams, to prevent students from cheating or engaging in unethical behavior. After consulting with experts and reviewing the online exam held in Covid-19 and other online exams, selected the four most common cheating activities found in the online exam. The study extracts key frames using motion-based frame extraction techniques before employing advanced deep learning techniques with various convolutional neural network configurations. This study presents several deep learning-based models that analyze the video exam to classify four categories of cheating. This method extracts key frames from a video sequence/stream based on human motion. This research developed a real dataset of cheating behaviours and conducted comprehensive experiments with pre-trained and suggested deep-learning models. When evaluated using standard performance criteria, the YOLOv5 model outperforms other pre-trained and fine-tuned approaches for detecting unusual activity. |
| first_indexed | 2024-03-08T02:04:18Z |
| format | Article |
| id | doaj.art-f5c8169b34bd414a81bcd1f55d97247a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T02:04:18Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f5c8169b34bd414a81bcd1f55d97247a2024-02-14T00:01:26ZengIEEEIEEE Access2169-35362024-01-0112215032151910.1109/ACCESS.2024.335968910416868Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online ExamsMuhammad Ramzan0https://orcid.org/0000-0003-1770-8905Adnan Abid1https://orcid.org/0000-0003-2602-2876Muhammad Bilal2https://orcid.org/0000-0002-9827-5023Khalid M. Aamir3Sufyan A. Memon4https://orcid.org/0000-0001-5592-9990Tae-Sun Chung5https://orcid.org/0000-0002-9827-5023Department of Software Engineering, Faculty of Computing and Information Technology, University of Sargodha, Sargodha, PakistanDepartment of Data Science, Faculty of Computing and Information Technology, University of the Punjab, Lahore, PakistanDepartment of Computing and Information Systems, School of Engineering and Technology, Sunway University, Petaling Jaya, Selangor, MalaysiaDepartment of Information Technology, Faculty of Computing and Information Technology, University of Sargodha, Sargodha, PakistanDepartment of Defense System Engineering, Sejong University, Seoul, South KoreaDepartment of Artificial Intelligence, Ajou University, Suwon-si, South KoreaOnline exams are growing increasingly popular in organizations and educational institutes because they are more flexible and cost-effective than conventional paper-based exams. When face-to-face exams are not possible, such as during floods, unexpected situations, or pandemics like COVID-19, this exam mod has become even more popular and important. However, online exams may have difficulties, such as the need for a reliable internet connection and the possibility of cheating. Because there is no human supervisor present to monitor the exam, so cheating is a major concern. The environment employed for the online exams ensures that every student finalizes the evaluation process without using any type of cheating. This study investigates the detection and recognition of unusual behavior in an academic setting, such as online exams, to prevent students from cheating or engaging in unethical behavior. After consulting with experts and reviewing the online exam held in Covid-19 and other online exams, selected the four most common cheating activities found in the online exam. The study extracts key frames using motion-based frame extraction techniques before employing advanced deep learning techniques with various convolutional neural network configurations. This study presents several deep learning-based models that analyze the video exam to classify four categories of cheating. This method extracts key frames from a video sequence/stream based on human motion. This research developed a real dataset of cheating behaviours and conducted comprehensive experiments with pre-trained and suggested deep-learning models. When evaluated using standard performance criteria, the YOLOv5 model outperforms other pre-trained and fine-tuned approaches for detecting unusual activity.https://ieeexplore.ieee.org/document/10416868/Online examsabnormal activitiescheatingcomputer visiondeep learningCNN |
| spellingShingle | Muhammad Ramzan Adnan Abid Muhammad Bilal Khalid M. Aamir Sufyan A. Memon Tae-Sun Chung Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams IEEE Access Online exams abnormal activities cheating computer vision deep learning CNN |
| title | Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams |
| title_full | Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams |
| title_fullStr | Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams |
| title_full_unstemmed | Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams |
| title_short | Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams |
| title_sort | effectiveness of pre trained cnn networks for detecting abnormal activities in online exams |
| topic | Online exams abnormal activities cheating computer vision deep learning CNN |
| url | https://ieeexplore.ieee.org/document/10416868/ |
| work_keys_str_mv | AT muhammadramzan effectivenessofpretrainedcnnnetworksfordetectingabnormalactivitiesinonlineexams AT adnanabid effectivenessofpretrainedcnnnetworksfordetectingabnormalactivitiesinonlineexams AT muhammadbilal effectivenessofpretrainedcnnnetworksfordetectingabnormalactivitiesinonlineexams AT khalidmaamir effectivenessofpretrainedcnnnetworksfordetectingabnormalactivitiesinonlineexams AT sufyanamemon effectivenessofpretrainedcnnnetworksfordetectingabnormalactivitiesinonlineexams AT taesunchung effectivenessofpretrainedcnnnetworksfordetectingabnormalactivitiesinonlineexams |