A Non-Intrusive Fuzzy Logic Framework for Real-Time Participant Engagement Assessment Using Multimodal Parameters

Classroom and training session engagement is difficult to measure objectively at scale, since traditional methods are either subjective or impractical for large groups. This study addresses that gap by developing a non-intrusive framework that includes participant engagement in real time from ordinary camera video. Three vision-derived behavioral indicators head-pose deviation, facial expression, and posture. Parameters are fuzzified using triangular and trapezoidal membership functions and combined through a Mamdani-type fuzzy inference system. The rule base and membership functions were validated through manual centroid calculation and cross-checked against a converged Python simulation; for a representative multi-rule case, the manual and simulated scores agreed to within 0.002%, and convergence analysis across discretization grid resolutions confirmed the numerical stability of the implementation. By combining lightweight camera-based feature extraction with an interpretable fuzzy inference layer, the proposed framework avoids the scalability limitations of sensor-based or manual assessment while explicitly modeling the uncertainty inherent in behavioral interpretation. The result is a practical, real-time engagement analytics tool that can support instructors and adaptive learning systems in identifying disengagement and personalizing intervention using contactless sensor.

Fuzzy Logic, Engagement Detection, Computer Vision, Mamdani Inference System, Multimodal Behavioral Analysis

1. Garcia-Ceja, E., Alvarado-Uribe, J., Escamilla-Ambrosio, P. J., Lara, A., Mena-Martinez, A., Gallegos-Garcia, G., Gonzalez-Mendoza, M., Monroy, R., Martinez Luna, G., & Fernández-Cárdenas, J. M. (2026). A dataset of university students' stress and anxiety levels based on questionnaires and wearable sensors. Scientific Data, 13(1), Article 732. https://doi.org/10.1038/s41597-026-07085-7 [Google Scholar] [Crossref]

2. Manikandan, S., & Vijayakumar, D. (2026). Secure cloud-based wearable sensor networks for teaching effectiveness evaluation in physical education through virtualized load balancer. International Journal of Computational Intelligence Systems, 19(1), Article 105. https://doi.org/10.1007/s44196-026-01230-1 [Google Scholar] [Crossref]

3. Wang, Y., Zhou, K., Lin, Z., Shen, H., Liu, R., Su, Z., Womer, F. Y., Wang, Y., Wei, Y., Zhu, R., Zheng, J., Zhang, X., & Wang, F. (2026). Evaluation of the efficacy of group cognitive behavioral therapy on anxiety in college students based on wearable devices and mobile applications: A randomized controlled trial. BMC Psychiatry, 26(1), Article 6. https://doi.org/10.1186/s12888-025-07572-y [Google Scholar] [Crossref]

4. Dan, Z., Yali, Z., & Tong, Z. (2026). 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, 38(5), Article 243. https://doi.org/10.1007/s44443-026-00639-0 [Google Scholar] [Crossref]

5. Bazhenova, G. A. (2026). The study of involvement in the educational process knowledge fatigue and the level of emotional intelligence of students using neural networks. Problemy Sotsial'noi Gigieny, Zdravookhraneniia i Istorii Meditsiny, 34, 371–377. https://doi.org/10.32687/0869-866X-2026-34-s1-371-377 [Google Scholar] [Crossref]

6. Duan, D. (2026). Using a predictive model based on fuzzy logic methods to test the mental health of students. Discover Computing, 29(1), Article 168. https://doi.org/10.1007/s10791-026-09962-6 [Google Scholar] [Crossref]

7. Deepakraj, J., Reddy, S. S., Khalil, B. T., Viswanadham, T. S., Balamurugan, M., & Mandal, R. (2025). Fuzzy logic and deep learning hybrid model for physiological stress detection in higher education. 2025 5th International Conference on Intelligent Technologies (CONIT). https://doi.org/10.1109/CONIT65521.2025.11167821 [Google Scholar] [Crossref]

8. Irhamsyah, M., Melinda, M., Zakaria, L. Q., Yunidar, Y., Koprawi, T. Y. P., & Miftahujjannah, R. (2025). A fuzzy logic-based stress recognition system for final-year students using PSS-10 neuropsychological measures. International Journal on Advanced Science, Engineering and Information Technology, 15(5), 1663–1671. https://doi.org/10.18517/ijaseit.15.5.20941 [Google Scholar] [Crossref]

9. Waqas, S. M., Alim, A., Talpur, K., Su'ud, M. M., Djenouri, Y., Ali, S. M., & Alam, M. M. (2026). A fuzzy membership-based enhancement to density peak clustering with comparative performance evaluation. Array, 30, Article 100785. https://doi.org/10.1016/j.array.2026.100785 [Google Scholar] [Crossref]

10. Şenel, A. A., Adiloğulları, G. E., & Şenel, E. (2026). Modelling the effect of motivation on mental health components with fuzzy logic among elite athletes. Scientific Reports, 16(1), Article 8076. https://doi.org/10.1038/s41598-026-39718-7 [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study