AI-Enabled Smart Classroom: Monitoring Mobile Phone Usage with Real-Time Alerts

The increasing use of mobile phones among students poses a challenge to maintaining focus and discipline in classrooms. This research proposes an AI- and IoT-powered Mobile
Detection and Monitoring System (MDMS) designed for academic environments. The system employs a three-tier IoT architecture for seamless sensing, processing, and monitoring. The Sensing Layer uses a camera module integrated with the YOLOv8 deep learning model to detect mobile phone usage in real time with high accuracy. Visual data are processed locally via an Edge AI Processing Unit, reducing latency and ensuring privacy. The Control Layer,
managed by an ESP32 microcontroller, executes a Timetable-Based Automation Algorithm (TBAA) to activate monitoring during lecture hours. A Violation Logging and Alert System
(VLAS) records repeated offenses and provides immediate notifications to teachers. The Application Layer features a teacher mobile app for live monitoring, violation tracking, and automated reports. Experimental results show that MDMS reduces distractions, improves discipline, and fosters a focused, AI-assisted learning environment.