Emotion-aware classroom quality assessment leveraging IoT-based real-time student monitoring

This work emphasizes system-level innovation, particularly in real-time deployment constraints, multi-agent coordination, and edge-based scalability in authentic classroom environments, while leveraging established deep learning models for robust performance. As large classroom sizes and limited teacher–student interaction increasingly challenge educators, there is a growing need for scalable, data-driven tools capable of capturing students’ emotional and engagement patterns in real time. The system was evaluated using the Classroom Emotion Dataset, a domain-specific dataset consisting of 1500 labeled images and 300 classroom detection videos captured in real-world Vietnamese K–12 classrooms, focusing on multi-person, in-the-wild affective interactions. Tailored for IoT devices, the system addresses load balancing and latency challenges through efficient real-time processing. Field testing was conducted across three educational institutions in a large metropolitan area: a primary school (hereafter school A), a secondary school (school B), and a high school (school C). The system demonstrated robust performance, detecting up to 50 faces at 25 FPS and achieving 88% overall accuracy in classifying classroom engagement states. Furthermore, the aggregated classroom engagement metric shows a strong correlation with expert annotations (Pearson , Spearman , ), exceeding the predefined threshold of 0.85, thereby confirming its reliability. Implementation results showed positive outcomes, with favorable feedback from students, teachers, and parents regarding improved classroom interaction and teaching adaptation. Key contributions of this research include establishing a practical, IoT-based framework for emotion-aware learning environments and introducing the ‘Classroom Emotion Dataset’ to facilitate further validation and research.