Abstract

The rapid shift toward online and remote academic assessment has exposed a significant gap between the convenience of digital examinations and the difficulty of preserving academic integrity without a physically present invigilator. This paper presents the design and implementation of an AI-Based Online Exam Proctoring System built on the MERN stack (MongoDB, Express.js, React, Node.js), intended for deployment in resource-constrained college environments. The system combines role-based access control for Admins, Teachers, and Students; a live webcam monitoring feed; browser-level behavioral detection (tab-switching, fullscreen exits, copy/paste and right-click attempts); a weighted violation-scoring algorithm that computes a real-time cheating percentage; automatic MCQ grading; and an auto-submission mechanism that terminates an exam attempt once a configurable violation threshold is crossed. Unlike many existing academic prototypes that isolate a single detection technique — facial recognition, eye-gaze tracking, or audio analysis — and depend on GPU-accelerated deep learning models, the proposed system integrates several lightweight, browser-native detection signals into a single, low-cost, self-hosted platform. Functional testing across ten core scenarios, from authentication to automated report emailing, confirmed correct end-to-end behavior. The result is a deployable, extensible proctoring platform suitable for final-year academic submission and small-to-medium scale institutional use, with a clear roadmap toward computer-vision-based enhancements

Views & downloads

012Nov 25: 0 ViewsDec 26: 0 ViewsJan: 0 ViewsFeb: 0 ViewsMar: 0 ViewsApr: 0 ViewsMay: 0 ViewsJun: 0 ViewsJul: 0 ViewsAug: 0 ViewsSep: 0 ViewsOct: 2 ViewsNov 25: 0 DownloadsDec 26: 0 DownloadsJan: 0 DownloadsFeb: 0 DownloadsMar: 0 DownloadsApr: 0 DownloadsMay: 0 DownloadsJun: 0 DownloadsJul: 0 DownloadsAug: 0 DownloadsSep: 0 DownloadsOct: 0 DownloadsNov 25Dec 26JanFebMarAprMayJunJulAugSepOct20
  • Article views
  • Full-text downloads

References

20 references
  1. [1] Atoum et al. — Automated Online Exam Proctoring
  2. [2] Prathish et al. — An Intelligent System for Online Exam Monitoring
  3. [3] Côté et al. — Video Summarization for Remote Invigilation of Online Exams
  4. [4] Pandey et al. — e-Parakh: Unsupervised Online Examination System
  5. [5] Dilini et al. — Cheating Detection in Browser-based Online Exams through Eye Gaze Tracking
  6. [6] Samir et al. — Exam Cheating Detection System with Multiple-Human Pose Estimation
  7. [7] Turani et al. — Students Online Exam Proctoring: A Case Study Using 360 Degree Security Cameras
  8. [8] Soltane & Laouar — A Smart System to Detect Cheating in the Online Exam
  9. [9] Gadkar et al. — Online Examination Auto-Proctoring System
  10. [10] Liu et al. — Multiple Instance Learning for Cheating Detection and Localization in Online Examinations
  11. [11] Ramzan et al. — Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams
  12. [12] Atabay & Hassanpour — Semi-Supervised Anomaly Detection in Electronic-Exam Proctoring Based on Skeleton Similarity
  13. [13] Alkilani & Nusir — Online Exam Monitoring System Based on Factor Analysis (FA) Method
  14. [14] Heya et al. — A Wearables-Driven Attack on Examination Proctoring
  15. [15] Castro & Manoharan — Observations of Cheating Behaviours in Online Examinations and Tools for Mitigation
  16. [16] Kong et al. — Design and Realization of an Online Examination System Based on Maven Framework2
  17. [17] Wen & Meng — Design and Implementation of Online Examination System Based on NET Framework Technology
  18. [18] Sirivarshitha et al. — An Approach for Face Detection and Face Recognition Using OpenCV and Face Recognition Libraries in Python
  19. [19] Deborah et al. — Secure Online Examination System for e-Learning
  20. [20] Ebron et al. — Anomaly Detection System for Possible Cheating During Online Examination

Data Availability Statement

Data availability: The data supporting this study are not publicly available. Any data used during system development and testing may be obtained from the corresponding author upon reasonable request, subject to applicable privacy and ethical restrictions.

How to Cite

PROCTOR AI-Based Online Exam Proctoring System: A MERN Stack Approach to Automated Academic Integrity Monitoring. (2026). Academic Research Journal of Science and Technology (ARJST), 5(07). https://doi.org/10.63300/arjst0507112026

Similar Articles

1-10 of 48

You may also start an advanced similarity search for this article.