International Journal of Engineering
Trends and Technology

Research Article | Open Access | Download PDF
Volume 74 | Issue 7 | Year 2026 | Article Id. IJETT-V74I7P102 | DOI : https://doi.org/10.14445/22315381/IJETT-V74I7P102

A Multimodal Deep Learning Framework for Real-Time Engagement and Environmental Adaptation in AI-Enabled Smart Classrooms

Kabaly P Subramanian, Walid Aboraya, Wasin Ayman Al Kishri, Ahmed Nasser Salem Al Kindi, Mahmood Al Bahri, Alfred Osta6, Amjid Ali

Received Revised Accepted Published
31 Oct 2025 21 Jan 2026 03 Jun 2026 28 Jul 2026

Citation :

Kabaly P Subramanian, Walid Aboraya, Wasin Ayman Al Kishri, Ahmed Nasser Salem Al Kindi, Mahmood Al Bahri, Alfred Osta6, Amjid Ali, "A Multimodal Deep Learning Framework for Real-Time Engagement and Environmental Adaptation in AI-Enabled Smart Classrooms," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 7, pp. 9-22, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I7P102

Abstract

The application of Artificial Intelligence (AI) technologies is speeding up in educational institutions, particularly in the realm of student engagement monitoring and adjusting classroom environments. Current systems are incapable of combining various modules for attendance tracking, perception of the environment, and behavior tracking, and keeping such modules independent while tracking in a classroom session. This study proposes a transformer-based modular deep learning system (Fusion-AttendNet) combining various environmental sensors, including temperature, humidity, dust, and CO₂, and visual behavioral cues from face detection and temporal signal, to provide real-time student engagement assessment, classroom comfort prediction, and actuator operations. The system utilizes cross-modal attention mechanisms and multitask learning to adaptively switch between model attention on different modalities and tasks. Experimental results show the proposed model outperforms the baseline LSTM, CNN, and BiLSTM models in terms of engagement classification performance, with 94.7% accuracy, and comfort prediction performance, with 0.121 RMSE, while processing in less than 10 milliseconds and achieving 96.2% actuator control operation precision. The framework successfully fills the gap in the related literature that lacks a deployment-ready solution which combines heterogeneous data streams for autonomous classroom management. This study proposes a single platform that combines sensory and behavioral data, using transformer architectures to create a basis for advanced environments that learn with AI.

Keywords

AI-enabled smart classroom, Multimodal Deep Learning, Transformer Architecture, Cross-Modal Attention, IoT Sensors, Intelligent Learning Environments.

References

[1] Divya Sharma et al., “Empowering Education: AI and IoT Integration for Smart Learning Environments,” Grenze International Journal of Engineering and Technology (GIJET), vol. 10, no. 2, 2024.
[Google Scholar]

[2] Maria Efstratopoulou et al., “In their Own Voices: A Nationwide Study of Students Attitudes Towards the Implementation of Smart Learning Environments in UAE Schools,” Smart Learning Environments, vol. 11, no. 1, pp. 1-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Kiran Budhrani, Yaeeun Ji, and Jae Hoon Lim, “Unpacking Conceptual Elements of Smart Learning in the Korean Scholarly Discourse,” Smart Learning Environments, vol. 5, no. 1, pp. 1-26, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Xieling Chen et al., “Past, Present, and Future of Smart Learning: A Topic-based Bibliometric Analysis,” International Journal of Educational Technology in High Education, vol. 18, no. 1, pp. 1-29, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Adam Kenneth Dubé, and Run Wen, “Identification and Evaluation of Technology Trends in K-12 Education from 2011 to 2021,” Educational Information Technology, vol. 27, no. 2, pp. 1929-1958, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Xiaomin Li, “Research on Intelligent Analysis Algorithm for Student Learning Behavior based on Multi-Source Sensor Data Fusion,” International Journal of High Speed Electronics and Systems, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Kashif Ishaq, and Samra Bibi, “IoT based Smart Attendance System using RFID: A Systematic Literature Review,” arXiv preprint, pp. 1-26, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[8] M.T. Miranda et al., “Ventilation Conditions and their Influence on Thermal Comfort in Examination Classrooms in Times of COVID-19. A Case Study in A Spanish Area with Mediterranean Climate,” International Journal of Hygiene and Environmental Health, vol. 240, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Sharmin Akter, and Asaduzzaman Asaduzzaman, “Internet of Things and Artificial Intelligence Enabled Smart Classroom,” 2023 6th International Conference on Electrical Information and Communication Technology (EICT), Khulna, Bangladesh, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Abhinaya Saravanan et al., “EduVigil: Shaping the Future of Education with AI - An Intriguing Case Study,” 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, pp.1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Tian-Tian Zhang, and Kai-Liang Zheng, “Learning Engagement through Multimodal Data Representation: A Theory-based Practical Framework,” International Journal of Advances in Engineering and Management (IJAEM), vol. 6, no. 11, pp. 232-241, 2024.
[CrossRef] [Google Scholar]

[12] Aboul Hassane CISSE, “Real-time Adaptive Learning Environments using Gaze and Emotion Recognition Engagement and Learning Outcomes,” International Conference on Computers in Education, pp. 1-4, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Saad Razzaq et al., “DeepClassRooms: A Deep Learning based Digital Twin Framework for on-Campus Class Rooms,” Neural Computing and Applications, vol. 35, no. 11, pp. 8017-8026, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Pedro David Netto Silveira et al., “Smart Learning Environments in Support of Learning Ecosystems,” Brazilian Symposium on Informatics in Education (SBIE). SBC, pp. 175-185, 2022.
[Google Scholar]

[15] Zhang Chao, Shi Qing, and Tong Mingwen, “A Study of Multimodal Intelligent Adaptive Learning System and its Pattern of Promoting Learners,” Journal of Psychology Research, vol. 13, no. 5, pp. 202-206, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Min Jae Lee, and Ruichuan Zhang, “Human-Centric Artificial Intelligence of Things–based Indoor Environment Quality Modeling Framework for Supporting Student Well-Being in Educational Facilities,” Journal of Computing in Civil Engineering, vol. 38, no. 2, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Kateryna Tanashchuk et al., “Adaptive Educational Ecosystems using Artificial Intelligence for Forming Students Educational Trajectories,” Humanity Management, vol. 25, no. 3, pp. 97-106, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Sucheta Yambal, and Yashwant Arjunrao Waykar, “AI-Driven Classroom Management: Balancing Efficiency, Engagement, and Ethics,” Impacts of AI on Students and Teachers in Education 5.0. IGI Global Scientific Publishing, pp. 93-124, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Koutraki Maria, Efthymiou Vasilis, and Antoniou Grigoris, “S-CRETA: Smart Classroom Real-Time Assistance,” Ambient Intelligence - Software and Applications: 3rd International Symposium on Ambient Intelligence (ISAmI 2012), Springer, Berlin, Heidelberg, vol. 153, pp. 67-74, 2012.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Gyeonggeon Lee et al., “Multimodality of AI for Education: Towards Artificial General Intelligence,” IEEE Transactions on Learning Technologies, vol. 18, pp. 666-683, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Stuart Hallifax et al., “Dynamic Gamification Adaptation Framework based on Engagement Detection through Learning Analytics,” Companion Proceedings of the 11th International Conference on Learning Analytics and Knowledge LAK21, pp. 1-14, 2021.
[Google Scholar] [Publisher Link]

[22] Flavio Corradini et al., “REPTILE: A Proactive Real-Time Deep Reinforcement Learning Self-Adaptive Framework,” arXiv preprint, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Deepti Chopra, and Praveen Arora, “Smart Classrooms, Smarter Teachers: A Deep Dive into AI-Driven Educational Enhancement,” Journal of Informatics Education and Research, vol. 3, no. 2, pp. 2813-2822, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Hazel Farrell, Re-Imagining Student Engagement in an AI-Enhanced Classroom, 1st ed., Using Generative AI Effectively in Higher Education, Routledge, pp. 67-73, 2024.
[Google Scholar] [Publisher Link]

[25] Deepti Chopra, and Praveen Arora, “Smart Classrooms, Smarter Teachers: A Deep Dive into AI-Driven Educational Enhancement,” Journal of Informatics Education and Research, vol. 3, no. 2, pp. 2813-2822, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Aida Akavova, Zarema Temirkhanova, and Zarina Lorsanova, “Adaptive Learning and Artificial Intelligence in the Educational Space,” E3S Web of Conferences, 2nd International Conference on Environmental Sustainability Management and Green Technologies (ESMGT 2023), vol. 451, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Lijuan Yan, Xiaotao Wu, and Yi Wang, “Student Engagement Assessment using Multimodal Deep Learning,” Plos One, vol. 20, no. 6, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Jue Wang, Yuchen Sun, and Shasha Tian, “Deep Learning for Student Behavior Detection in Smart Classroom Environments,” Information, vol. 16, no. 11, pp. 1-23, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Zhao Dan, Zhao Yali, and Zhao Tong, “A Multimodal AI Framework for Real-Time Student Engagement Detection and Adaptive Feedback in Higher Education,” Journal of King Saud University Computer and Information Sciences, vol. 38, no. 5, pp. 1-40, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Kuan-Cheng Lin, Chiung-Chen Tseng, and Junyi Wu, “A Scalable Multimodal Framework for Learning Engagement Recognition using Three-Dimensional Convolutional Neural Networks and Semi-automatic Annotation,” Frontiers in Artificial Intelligence, vol. 9, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Muddsair Sharif, and Dieter Uckelmann, “Multi-Modal LA in Personalized Education using Deep Reinforcement Learning based Approach,” IEEE Access, vol. 12, pp. 54049-54065, 2024.
[CrossRef] [Google Scholar] [Publisher Link]