International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 04 | Apr 2025
p-ISSN: 2395-0072
www.irjet.net
MERN DRIVEN AI EXAM PROCTORING SYSTEM Shreeram Mutukundu1, Ankush Tiwari2, Adarsh Kumbhar3, Swati Khairnar4 1Student, Dept. of Computer Engineering, JSPM’s Imperial College of Engineering and Research, Wagholi, Pune,
Maharashtra, India
2Student, Dept. of Computer Engineering, JSPM’s Imperial College of Engineering and Research, Wagholi, Pune,
Maharashtra, India
3Student, Dept. of Computer Engineering, JSPM’s Imperial College of Engineering and Research, Wagholi, Pune,
Maharashtra, India
4Professor, Dept. of Computer Engineering, JSPM’s Imperial College of Engineering and Research, Wagholi, Pune,
Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In recent years, online examinations have
sending instant alerts if it detects any irregularities, such as unauthorized movements or external assistance. In doing so, it creates an environment where academic integrity is preserved without compromising on the user experience. This blend of artificial intelligence with the flexibility of web technologies ensures a solution that not only adapts to various testing scenarios but also evolves with future technological advancements.
gained significant popularity due to their flexibility, especially during the COVID-19 pandemic. However, ensuring cheating-free exams remains a major challenge for educational institutions. In this paper, we propose an AIbased proctoring system that eliminates the need for continuous human supervision. Leveraging neural networks and machine learning techniques, the system can detect any unethical behavior during an exam, such as eye movement tracking, mouth movement, and device usage. Our experiments demonstrate that this system outperforms traditional proctoring methods, enhancing exam integrity and security.
By shifting from reactive monitoring to proactive surveillance, our research introduces a novel approach to online exam security. The AI proctor doesn’t merely observe; it actively engages with the examination process, ensuring that any signs of misconduct are flagged immediately. This proactive model empowers educational institutions to offer secure, scalable, and fair assessments, no matter the size of the exam or the location of the students. As online education continues to evolve, this research lays the groundwork for a future where automated systems uphold the principles of fairness, accessibility, and trust in digital learning environments.
Key Words: AI proctoring, cheating detection, machine learning, online exam security, proctoring automation, real-time monitoring
1.INTRODUCTION This research tackles the rising challenge of academic dishonesty in remote exams, an issue that has grown significantly with the widespread shift to online education. Traditional methods of exam proctoring, which rely heavily on human invigilators, have proven to be inefficient and impractical in an increasingly digital world. To address this, we propose an innovative solution—an AI-powered proctor system that blends seamlessly with online exam platforms. This system is designed to monitor students in real-time, detecting any suspicious behavior and ensuring the integrity of the examination process. Through advanced algorithms and machine learning techniques, the AI proctor is capable of analyzing facial expressions, screen activities, and even background anomalies, offering a level of vigilance that human proctors simply cannot match.
2. LITERATURE REVIEW In research paper [1], the authors highlight the challenges posed by online education, particularly during the COVID19 pandemic, which forced educational institutions to shift to online learning and examinations. This transition brought forward concerns regarding academic integrity, as students could potentially engage in cheating through various means such as hiring services to write papers or take exams on their behalf. The paper emphasizes the importance of developing effective solutions, particularly AI-based proctoring systems, to maintain the integrity of online assessments. It discusses the necessity of secure, non-intrusive proctoring techniques like facial recognition and behaviour analysis to deter cheating during online exams.
The core of our project is the integration of AI with the MERN stack, which provides a scalable and secure framework for creating a robust, real-time exam monitoring system. The AI model continuously tracks and evaluates candidate behavior throughout the exam,
© 2025, IRJET
|
Impact Factor value: 8.315
In paper [2], the authors propose an AI-based online exam proctoring system, aimed at ensuring the security and authenticity of remote assessments. The system utilizes
|
ISO 9001:2008 Certified Journal
|
Page 1258