An Enhanced Web-Based Examination System using Automated Proctoring and Background Activity Detection

Abstract

The rise of online education demands sturdy systems to uphold academic integrity during remote assessments. This paper presents the design and implementation of a web-based examination platform integrated with automated, multi-modal proctoring tools to detect potential cheating. The system enables educators to create and manage diverse assessments while students’ complete exams in a monitored virtual environment. Key security measures include user authentication with facial recognition using the DeepFace library and continuous webcam analysis to detect mobile phone usage, unauthorized individuals, and unusual head or eye movements. Additional features include browser focus tracking to monitor navigation away from the exam window, and background audio analysis using Voice Activity Detection (VAD) and Root Mean Square (RMS) energy to flag suspicious sounds or conversations. Detected anomalies are logged in real-time for review. The prototype effectively combines visual, auditory, and behavioral monitoring into a cohesive framework, offering a comprehensive solution to reduce academic misconduct in remote settings. Functional testing showed 72% overall system accuracy and over 90%+ accuracy in specific detection modules. Future work should intend to enhance the system's AI capabilities, improve performance on models, and ensure fairness for all users, contributing to credible and secure digital learning environments across disciplines.