• P Krishnamoorthy
• G. Pavani
• U. Praveen Kumar
• N.Naga Sree Nithya
• B. Vamsi

Abstract: The increasing use of technology in exam halls has posed new challenges for ensuring academic integrity. This literature survey focuses on detecting suspicious activities to prevent malpractice in exam settings. The study examines various approaches, including machine learning (ML), deep learning (DL), and behavioral monitoring technologies. Key detection methods such as eye-tracking, activity recognition, and real-time monitoring systems are explored, evaluating their effectiveness in identifying cheating behaviors. Additionally, this paper reviews existing research and discusses implementation methodologies for these technologies in exam halls. Findings suggest that integrating multiple detection techniques enhances the accuracy of identifying suspicious activities and reduces the occurrence of malpractice. This review underscores the potential of advanced technologies in improving exam security while ensuring fairness in academic assessments.

"A Review of Machine Learning Techniques for Detecting Suspicious Activities in Exam Halls to Prevent Malpractice", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.c824-c830, December-2024, Available :http://www.jetir.org/papers/JETIR2412295.pdf

"A Review of Machine Learning Techniques for Detecting Suspicious Activities in Exam Halls to Prevent Malpractice", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppc824-c830, December-2024, Available at : http://www.jetir.org/papers/JETIR2412295.pdf