A Temporal Facial Engagement Analysis Framework for Pedagogical Feedback in Smart Classroom

Author(s)	Ms. Manisha Bhaskar More, Dr. Bali Thorat
Country	India
Abstract	Traditional classrooms lack real-time mechanisms to quantify student engagement, limiting instructors' ability to adapt teaching dynamically. This paper proposes a temporal facial engagement analysis framework that processes classroom videos from 20 students using MTCNN for face detection, InceptionResnetV1 for recognition, and LSTM networks for temporal emotion modelling. The system computes per-student attendance, engagement trajectories, and class-wide averages to generate actionable pedagogical feedback. This real-time insight enhances the overall effectiveness of the teaching–learning process by making it more responsive and student-centred. Furthermore, the system contributes to improved learning outcomes by facilitating timely pedagogical interventions whenever signs of disengagement are detected. Validated on unconstrained classroom footage, the framework achieves 88% emotion recognition accuracy and 92% attendance precision, surpassing static methods by 15%. Edge deployment on Raspberry Pi demonstrates 25 fps inference, confirming practical viability for smart classroom integration.
Keywords	temporal engagement analysis, facial emotion recognition, LSTM, MTCNN, smart classrooms, pedagogical feedback, edge computing.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 17, Issue 2, April-June 2026
Published On	2026-05-28

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology