AI Powered Personalized Learning Path Generator

This research proposes a closed-loop, AI-powered academic framework that incorporates secure attendance monitoring and personalized learning. It views attendance as an early warning system, unlike most systems.   The system integrates multi-factor verification with AI-driven, syllabus-aligned learning paths to provide adaptive and targeted support. Attendance reliability, engagement, and academic performance improvements were observed in experimental studies.

[1] K. S. Yadav, A. Singh, and R. Verma, “Face Recognition Based Attendance System Using Deep Learning,” Procedia Computer Science, vol. 167, pp. 1646–1654, 2020. https://doi.org/10.1016/j.procs.2020.03.375   [2] J. Deng, J. Guo, and S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” in Proc. IEEE CVPR, 2019. https://doi.org/10.1109/CVPR.2019.00482   [3] P. Brusilovsky, “Adaptive Educational Systems on the World Wide Web,” IJAIED, 2001. https://link.springer.com/article/10.1023/A:1011143116306   [4] C. Piech et al., “Deep Knowledge Tracing,” in NeurIPS, 2015. https://papers.nips.cc/paper/5654-deep-knowledge-tracing   [5] Z. A. Pardos and N. T. Heffernan, “Modeling Individualization in Knowledge Tracing,” 2010. https://link.springer.com/chapter/10.1007/978-3-642-13470-8_24   [6] R. S. Baker and K. Yacef, “Educational Data Mining and Future Visions,” JEDM, 2009. https://jedm.educationaldatamining.org/index.php/JEDM/article/view/8   [7] OpenAI, “GPT-4 Technical Report,” 2023. https://arxiv.org/abs/2303.08774   [8] T. Brown et al., “Language Models are Few-Shot Learners,” NeurIPS, 2020. https://papers.nips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html   [9] J. Wei et al., “Chain-of-Thought Prompting,” NeurIPS, 2022. https://arxiv.org/abs/2201.11903   [10] R. Fielding, “Architectural Styles and the Design of Network-based Software Architectures,” 2000. https://www.ics.uci.edu/~fielding/pubs/dissertation/top.htm