AI-Driven Online Exam Monitoring System with AttentionBased Multi-Scale Feature Fusion

Abstract

AI-Driven Online Exam Monitoring System presents a fundamental challenge in AI, Computer Vision, E-Learning. Existing approaches, including MediaPipe+DT, OpenFace+SVM, and MTCNN+RF, process input data at a single resolution and fail to capture patterns spanning multiple scales, resulting in a mean accuracy ceiling on benchmark datasets. We address this limitation by introducing ExamGuard, a hybrid deep learning framework that integrates three parallel convolutional streams (kernel sizes 3, 7, and 13) with bidirectional LSTM encoding and a gated attention fusion module. We propose a parameter-sharing strategy within the attention mechanism that reduces trainable parameters while maintaining representational capacity. We train and evaluate our framework on Custom Exam, CASIA using stratified 10-fold crossvalidation. Our method achieves a mean detection acc. (%) of 92.5% on the primary benchmark, surpassing the nearest baseline by 6.1 percentage points (p < 0.001, Cohen's d = 1.42). We further demonstrate a 30.2% reduction in computational cost relative to comparable hybrid architectures and convergence within 105 epochs on all benchmark datasets.