Real-time classroom learning-state perception can help teachers notice changes in whole-class participation, but systems based on individual identification, facial analysis, or cloud transmission create privacy and governance risks. This paper presents a privacy-preserving edge computing framework for group-level classroom learning-state perception and teacher decision support. The study does not report completed classroom-effectiveness results. Instead, it develops a design framework that can be tested in later pilots. The framework was derived from learning analytics, classroom engagement, teacher decision-support, multimodal learning analytics, edge computing, and artificial intelligence (AI) governance literature. It specifies a five-layer architecture, a local data-flow boundary, window-level feature definitions, indicator computation formulas, a rule-based teacher-prompt mechanism, and a pilot evaluation protocol. The system processes millimeter-wave radar, speech-energy patterns, and interaction logs at a classroom edge node, then outputs aggregated indicators such as attention trend, activity level, participation balance, and rhythm fluctuation. Raw signals are deleted after feature extraction, and teacher prompts are advisory, dismissible, and traceable. The contribution of the paper is a more explicit and testable design specification for privacy-first classroom analytics, rather than an unverified claim of instructional effectiveness.
References
[1] Wang, P., Viberg, O., Law, E. L. C., Greiff, S. (2026) When can ai models explain learning? Validity criteria for ai as cognitive models in education. Educational Psychology Review, 38(1), 106.
[2] Radwan, A., Mcginty, J. (2024) Toward a conceptual generative AI ethical framework in teacher education. Exploring New Horizons: Generative Artificial Intelligence and Teacher Education, 88.
[3] Guberina, T., Procházka, F. (2026) Human-AI collaborative teaching: generative artificial intelligence (Gen-AI) as co-teacher. Social Science Chronicle, 6, 1-19.
[4] Romero, C., Ventura, S. (2020) Educational data mining and learning analytics: an updated survey. Wiley Interdisciplinary Reviews: Data Mining And Knowledge Discovery, 10(3), e1355.
[5] Finck, M., Biega, A. J. (2021) Reviving purpose limitation and data minimisation in data-driven systems. Technology and Regulation, 2021, 44-61.
[6] Sunyaev, A., Benlian, A., Pfeiffer, J., Jussupow, E., Thiebes, S., Maedche, A., Gawlitza, J. (2025) High-Risk Artificial Intelligence: Ali Sunyaev et al. Business & Information Systems Engineering, 67(6), 981-994.
[7] Joksimović, S., Kovanović, V., Dawson, S. (2019) The journey of learning analytics. HERDSA Review of Higher Education, 6, 27-63.
[8] Isohätälä, J., Näykki, P., Järvelä, S. (2020) Cognitive and socio-emotional interaction in collaborative learning: Exploring fluctuations in students’ participation. Scandinavian Journal of Educational Research, 64(6), 831-851.
[9] Kim, J. (2024) Leading teachers’ perspective on teacher-AI collaboration in education. Education and Information Technologies, 29(7), 8693-8724.
[10] Cabral, L., Pinto, R., Gonçalves, G. (2025) AI-powered learning analytics dashboards: a systematic review of applications, techniques, and research gaps. Discover Education, 4(1), 525.
[11] Fry, M., Wang, C. X., Vasquez, S., Shaffer, J., Clark, A., Wolfe, R., Reynolds, E. (2026) Faculty Lived Experiences with Mixed-Reality Simulation in Teacher Preparation: An Interpretive Phenomenology. Journal of Technology and Teacher Education, 34(1), 5-46.
[12] Vargas, E. G., Chiappe, A., Durand, J. (2024) Reshaping education in the era of artificial intelligence: insights from Situated Learning related literature. Journal of Social Studies Education Research, 15(2), 1-28.
[13] Wright, E., Taffe, S., Luxton, S., Wragg, N. (2026) Embedding authentic learning: A case study in curriculum transformation. Education Sciences, 16(3), 392.
[14] Van Zyl, L. E. (2026) The AI-IARA framework: How to cultivate human agency before artificial intelligence optimizes it a (ny) way. The Journal of Positive Psychology, 1-19.
[15] Guerrero-Sosa, J. D., Romero, F. P., Menéndez-Domínguez, V. H., Serrano-Guerrero, J., Montoro-Montarroso, A., Olivas, J. A. (2025) A comprehensive review of multimodal analysis in education. Applied Sciences, 15(11), 5896.
[16] Becerra, A., Cobos, R., Lang, C. (2026) Enhancing online learning by integrating biosensors and multimodal learning analytics for detecting and predicting student behaviour: a review. Behaviour & Information Technology, 45(9), 1885-1910.
[17] Chiang, Y., Zhang, Y., Luo, H., Chen, T. Y., Chen, G. H., Chen, H. T., Chou, C. T. (2023) Management and orchestration of edge computing for IoT: a comprehensive survey. IEEE Internet of Things Journal, 10(16), 14307-14331.
[18] Tarapder, S. A. (2026) EDGE artificial intelligence based automation for ultra-low-latency control in industrial robotic systems. Review of Applied Science and Technology, 5(01), 01-37.
[19] Chen, J., Yan, H., Liu, Z., Zhang, M., Xiong, H., Yu, S. (2024) When federated learning meets privacy-preserving computation. ACM Computing Surveys, 56(12), 1-36.
[20] Bellavista, P., Foschini, L., Mora, A. (2021) Decentralised learning in federated deployment environments: a system-level survey. ACM Computing Surveys (CSUR), 54(1), 1-38.
[21] Matcha, W., Uzir, N. A. A., Gašević, D., Pardo, A. (2019) A systematic review of empirical studies on learning analytics dashboards: A self-regulated learning perspective. IEEE Transactions on Learning Technologies, 13(2), 226-245.
[22] Hevner, A. R., March, S. T., Park, J., Ram, S. (2004) Design science in information systems research1. MIS Quarterly, 28(1), 75-106.
[23] Hossain, F., Anagnostou, E. N., Dinku, T., Borga, M. (2004) Hydrological model sensitivity to parameter and radar rainfall estimation uncertainty. Hydrological Processes, 18(17), 3277-3291.
[24] Zhao, C., Shen, W. (2023) Federated domain generalization: a secure and robust framework for intelligent fault diagnosis. IEEE Transactions on Industrial Informatics, 20(2), 2662-2670.
[25] Li, C. (2025) AI-driven governance: Enhancing transparency and accountability in public administration. Digital Society & Virtual Governance, 1(1), 1-16.
[26] McCrary, Q. D. (2026) Are we ghosts in the machine? AI, agency, and the future of libraries. The Journal of Academic Librarianship, 52(1), 103181.
Share and Cite
Zhang Z., Jiang C., Shen Y. (2026) A Privacy-preserving Edge Computing Framework for Group-level Classroom Learning-state Perception and Teacher Decision Support. Global Education Bulletin, 3(2), 97-115. https://doi.org/10.71052/grb2025/TJTU6716