Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64897
Volume:
10 |
6 |
Jun 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Information Technology
4127 - TAGORE ENGINEERING COLLEGE
Department of Information Technology
4127 - TAGORE ENGINEERING COLLEGE
Department of Information Technology
4127 - TAGORE ENGINEERING COLLEGE
Traditional educational systems struggle to deliver personalized learning and real-time feedback, relying on post-hoc assessments that fail to detect cognitive overload or disengagement during instruction, particularly in online and hybrid environments intensified by COVID-19. Increasing teacher workload, larger class sizes, and limited institutional resources further restrict individualized attention and timely intervention. This paper presents the Smart Learning Application, an AI-driven educational platform that integrates real-time cognitive monitoring, computer vision–based eye tracking, and adaptive learning algorithms within a multi-tier architecture using FastAPI, SQLite, responsive web interfaces, OpenCV for face and eye detection, and Google Gemini AI for intelligent tutoring. Cognitive load is calculated using gaze tracking and attention metrics grounded in cognitive load theory to ensure pedagogical alignment. Experimental and longitudinal evaluations demonstrate 85–90% correlation between automated cognitive load detection and self-reported engagement, 3-second interval video processing for continuous monitoring, 92% user satisfaction with AI-assisted tutoring, 25% improvement in learning outcomes compared to non-adaptive systems, and 40% improvement in teachers’ ability to identify students requiring support. The findings confirm sustained improvements in self-regulation and cross-cultural applicability with necessary regional adaptations. The proposed system advances learning analytics and educational data mining by enabling ethical, data-driven, and personalized instructional strategies.
KEYWORDS
This research demonstrates that integrating real-time cognitive monitoring with adaptive AI learning significantly enhances educational outcomes. The system achieved 85–90% cognitive load accuracy and 25% improvement in learning performance while maintaining ethical data practices and scalable deployment architecture. The Smart Learning Application illustrates how advanced technologies can responsibly support human teaching rather than replace it, promoting personalized, equitable, and adaptive education at scale.
[1] "Adaptive Interface Model with Eye-Tracking Evaluation," in Proc. IEEE, 2019.Available: https://ieeexplore.ieee.org/document/897989 8/ [2] "Eye-Tracking in STEM Education Research: Limitations, Experiences and Possible Extensions," in Proc. IEEE, 2014. Available: https://ieeexplore.ieee.org/document/700955 0/ [3] "ML-based Classification of Eye Movement Patterns During Reading Using Eye Tracking Data," in Proc. IEEE, 2021.Available: https://ieeexplore.ieee.org/document/959941 7/ [4] "Deep Learning Methods for the Prediction of Information Display Type Using Eye Tracking Sequences," in Proc. IEEE, 2021.Available: https://ieeexplore.ieee.org/document/968025 6/ [5] "Automated Recording and Semantics-Aware Replaying of High-Speed Eye Tracking and Interaction Data," in Proc. IEEE,2020.Available: https://ieeexplore.ieee.org/document/924062 4/ [6] "Cognitive Assessment Based on Eye Tracking Using Device-Embedded Cameras via Tele-Neuropsychology," in IEEE Xplore, 2024. Available: https://ieeexplore.ieee.org/document/109544 60/ [7] T. Van Gog and K. Scheiter, "Eye tracking as a tool to study and enhance multimedia learning," Learning and Instruction, vol. 20, no. 2, pp. 95–99, Apr. 2010. [Link: https://www.sciencedirect.com/science/article/pii /S0959475209000570] [8] K. Rayner, "Eye movements in reading and information processing: 20 years of research," Psychological Bulletin, vol. 124, no. 3, pp. 372–422, Nov. 1998. [Link: https://psycnet.apa.org/record/1998-11551-003] [9] P. Ekman, "An argument for basic emotions," Cognition & Emotion, vol. 6, no. 3-4, pp. 169–200, 1992. [Link: https://www.tandfonline.com/doi/abs/10.1080/0 2699939208411068] [10] S. K. D'mello and A. Graesser, "Dynamics of affective states during complex learning," Learning and Instruction, vol. 22, no. 2, pp. 145–157, Apr. 2012. [Link: https://www.sciencedirect.com/science/article/pi i/S0959475211000757]
Publication Date
6/12/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...