Date
Publisher
arXiv
The increasing adoption of smart classroom technologies in higher education has mainly focused on automating attendance, with limited attention given to students' emotional and cognitive engagement during lectures. This limits instructors' ability to identify disengagement and adapt teaching strategies in real time. This paper presents SCASED (Smart Classroom Attendance System with Emotion Detection), an IoT-based system that integrates automated attendance tracking with facial emotion recognition to support classroom engagement monitoring. The system uses a Raspberry Pi camera and OpenCV for face detection, and a finetuned MobileNetV2 model to classify four learning-related emotional states: engagement, boredom, confusion, and frustration. A session-based mechanism is implemented to manage attendance and emotion monitoring by recording attendance once per session and performing continuous emotion analysis thereafter. Attendance and emotion data are visualized through a cloud-based dashboard to provide instructors with insights into classroom dynamics. Experimental evaluation using the DAiSEE dataset achieved an emotion classification accuracy of 89.5%. The results show that integrating attendance data with emotion analytics can provide instructors with additional insight into classroom dynamics and support more responsive teaching practices.
Study at a glance
- Question: Can an affordable smart classroom system track student attendance and detect learning-related emotions in real time?
- Setting and data: 138 video clips (1,380 image frames) from the DAiSEE dataset; prototype testing on Raspberry Pi hardware.
- Method: System development and prototype evaluation using computer vision and deep learning.
Why it matters
Automated attendance confirms physical presence but does not capture student attention or comprehension. Current smart classroom technologies rarely combine attendance tracking with real-time emotion monitoring on affordable classroom hardware to help instructors identify disengagement.
Key findings
- The fine-tuned MobileNetV2 model achieved 89.5% accuracy in classifying engagement, boredom, confusion, and frustration on the DAiSEE test set.
- Engagement and confusion were recognized with the highest precision and recall, achieving F1-scores of 0.92 and 0.90, respectively.
- Testing showed the system reliably marked student attendance once upon first detection and continuously tracked emotions thereafter without duplicate attendance records.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
