Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178108,
        author = {Rutuja Gangane and Rutuja Rajabhau Kadu and Rashmi Vilas Yeole and Dhanashri Ramdas Gaikwad},
        title = {Suspicious Activity Detection In Online Exams},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {2819-2822},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178108},
        abstract = {The rise of online exams has made it necessary to ensure their integrity and fairness. This project focuses on detecting cheating during online examinations without the need for physical supervision. Our goal is to develop a system that can analyze video feeds of exam takers in real time to identify any suspicious activities that may indicate dishonest behaviour. We will collect data from video streams, which will be processed to detect any suspicious actions. Using advanced techniques like o ensure exam integrity, including PHP for web development, Flask for proctoring, and YOLOv8 for real-time person detection. which are effective for understanding sequences of events over time. Additionally, Support Vector Machines (SVM) and Random Forest algorithms will be used for analysing structured data, providing reliable models for identifying abnormal behaviour. Hidden Markov Models (HMM) will be utilized to monitor audio data, capturing any verbal cues that could suggest cheating. To build this system, we will use programming languages such as Php, Mysql and Html,Css, JavaScript, along with frameworks like flask and OpenCV. Our methodology includes several steps: data collection, preprocessing, feature extraction, model selection, real-time detection, and rigorous training and testing of the models. Ultimately, this project aims to ensures a secure online examination environment by integrating advanced monitoring technologies. The combination of PHP, Flask, and YOLOv8 enhances security, making cheating difficult. Future enhancements could include AI-based behavior analysis and voice detection.},
        keywords = {},
        month = {May},
        }