Intelligent Student Management System with IoT and Machine Learning

Abstract

The unification of Internet of Things (IoT) and machine learning technologies is reshaping educational environments, empowering smart classrooms and efficient campus management. However, traditional student management systems often rely on manual processes for attendance tracking and lack predictive competences to categorize at-risk students. This paper proposes an Intelligent Student Management System that leverages IoT devices, such as ESP cameras and Wi-Fi Mesh networks, coupled with machine learning model, to automate attendance tracking and predict student academic performance. The system employs Face Acquisition Systems (FAS) connected to a Main Management Console (MMC) through a Wi-Fi Mesh network. Each FAS includes an ESP camera with a microcontroller programmed to execute machine learning model (MLM) for real-time student identification and attendance recording. The MMC analyses historical academic data, including grades and attendance records, to predict future performance and identify students at risk of underperforming. The system provides actionable insights to educators and parents, enabling timely interventions to support student success. Experimental results validate high accuracy in attendance tracking (98.5%) and performance prediction (92%), showcasing the system’s potential to transform student management in educational establishments. This research highlights the transformative budding of IoT and machine learning in creating intelligent, data-driven educational environments.