Intelligent Classroom Monitoring System for Enhanced Learning Environments Using Deep Learning

With the growing emphasis on enhancing educational quality and engagement, traditional classroom monitoring methods fall short due to their subjectivity, inconsistency, and limited scalability. This project introduces an AI-supported intelligent classroom monitoring system that automates the evaluation of student attentiveness, instructor activity, and attendance. The system leverages classroom video feeds, processed using Convolutional Neural Networks (CNN) for activity detection and FaceNet for facial recognition and identification. A real-time dashboard interface provides visual analytics, supporting educators in making informed decisions. Trained on a custom dataset of over 10,000 labeled images, the model achieved more than 95% classification accuracy. The solution demonstrates the potential of AI to foster data-driven, transparent, and engaging learning environments that improve academic outcomes and institutional efficiency.