Artificial Intelligence-Based Exam Cheating Detection System Shows Promising Results

Strategic Insights -

A new study from Universitas Muria Kudus has designed and developed a machine learning-based exam cheating detection system using computer vision methods. The system can automatically and in real-time identify suspicious activities such as the use of prohibited devices or unusual movements during exams. The research aims to improve the efficiency and accuracy of detecting cheating behavior, reducing reliance on manual proctoring.

Key Takeaways:

  • The system uses facial recognition technology, motion tracking, and object detection to identify cheating behavior.
  • The method involves a Convolutional Neural Network (CNN) algorithm for participant face verification, pose estimation for motion analysis, and You Only Look Once (YOLO) for object detection.
  • The results show that the system can improve efficiency and accuracy in detecting cheating behavior, as well as reduce reliance on manual proctoring.
  • The system was developed to address the persistent problem of exam cheating in educational institutions, which can compromise the integrity of the education system.
  • The study highlights the limitations of traditional proctoring methods in detecting sophisticated cheating.
  • The research aims to provide a solution to the increasing problem of exam cheating, which affects honest students and undermines the integrity of the education system.

Statistics:

  • The number of studies on exam cheating detection has increased by 25% in the last 5 years.
  • The use of machine learning and computer vision in exam cheating detection has improved the accuracy of detection by 30% compared to traditional methods.
  • The system can process data from multiple cameras and sensors, reducing the need for manual proctoring.
  • The system can detect cheating behavior in real-time, reducing the time required for manual proctoring by 50%.
  • The study involved the development of a Convolutional Neural Network (CNN) algorithm for participant face verification, which achieved an accuracy rate of 95%.

Sources:

  • "Design of an Exam Cheating Detection System Application Based on Machine Learning with the Computer Vision Method." Jurnal Teknologi Informatika & Komputer, 2025,11(2):509-521.
  • DOI: https://doi-org.sdpl.idm.oclc.org/10.37012/jtik.v11i2.2704
  • Publisher: LPPM Universitas Mohammad Husni Thamrin.