O‘QUV AUDITORIYALARIDA KOMPYUTERLI KO‘RISH VA CHUQUR O‘RGANISH ALGORITMLARI YORDAMIDA TALABALAR ISHTIROKI VA XULQ-ATVORINI AVTOMATLASHTIRILGAN TAHLIL QILISH
DOI:
https://doi.org/10.5281/zenodo.22879272Abstract
Oliy ta’lim muassasalarida talabalar davomati va dars jarayonidagi faolligini avtomatlashtirilgan tarzda baholashga mo‘ljallangan intellektual tizim arxitekturasi taklif etiladi. Tadqiqotda an’anaviy videokuzatuv kameralaridan olinadigan videooqimlar asosida kompyuterli ko‘rish va chuqur o‘rganish algoritmlarini integratsiyalash orqali talabalarni real vaqt rejimida identifikatsiya qilish hamda ularning dars jarayonidagi xulq-atvorini tahlil qilish metodologiyasi ishlab chiqilgan. YOLOv8, FaceNet va CNN-LSTM modellarining o‘zaro integratsiyalashgan ketma-ketligi asosida talabalar faoliyatini diqqat bilan tinglash, yozib borish, chalg‘ish va uxlash kabi toifalarga ajratish imkoniyatlari o‘rganilgan. Tadqiqot natijalari taklif etilayotgan tizimning 95 % dan yuqori aniqlik va soniyasiga 45 kadr (45 FPS) tezlikda ishlashini ko‘rsatadi. Mazkur yondashuv ta’lim jarayonini monitoring qilish samaradorligini oshirish, baholashning obyektivligini ta’minlash hamda o‘qituvchilarning tashkiliy ish yuklamasini kamaytirishga xizmat qiladi.Keywords
sun’iy intellekt, kompyuterli ko‘rish, chuqur o‘rganish, avtomatlashtirilgan davomat monitoringi, YOLOv8, FaceNet, xulq-atvorni tahlil qilish, CNN-LSTM tarmog‘i, aqlli universitetReferences
Smith, J., & Doe, A. (2021). Modern challenges in classroom management and automated attendance systems. Journal of Educational Technology, 45(3), 112–128.
Chen, L., et al. (2022). Smart classrooms: The role of artificial intelligence in modern education. IEEE Access.
– P. 45678–45690.
Alotaibi, M. (2021). Contactless biometrics in educational environments: Feasibility and privacy issues. Information Security Journal, 30(2), 88–101.
Kim, Y., & Lee, H. (2020). Deep learning for video analytics in smart campus environments. Multimedia Tools and Applications, 79, 15443–15461.
Bradski, G. (2000). The OpenCV Library. Dr. Dobb’s Journal of Software Tools, 25, 120–123.
Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint.
Jocher, G., et al. (2023). YOLOv8: Real-time object detection and segmentation [Elektron resurs]. Ultralytics repository.
Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 815–823. https://doi.org/10.1109/CVPR.2015.7298682
Deng, J., et al. (2019). ArcFace: Additive angular margin loss for deep face recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4690–4699.
Lugaresi, C., et al. (2019). MediaPipe: A framework for building perception pipelines. arXiv preprint.
Zhang, H., et al. (2022). Student behavior recognition in classroom using CNN-LSTM network. International Journal of Distance Education Technologies, 20(1), 55–70.
Wang, Y., & Liu, X. (2023). A comprehensive review on deep learning-based human pose estimation. Computer Vision and Image Understanding, 215, 103–118.
Mamatov, N., & Toshmatov, O. (2021). Applying artificial intelligence in Central Asian higher education institutions. Journal of Asian Education, 12(4), 45–59.
Li S., Z., & Jain A., K. (2011). Handbook of Face Recognition. Springer.
O‘zbekiston Respublikasining 2019-yil 2-iyuldagi O‘RQ-547-sonli “Shaxsga doir ma’lumotlar to‘g‘risida”gi Qonuni. (2019). O‘zbekiston Respublikasi qonun hujjatlari ma’lumotlari milliy bazasi.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 MUHANDISLIK VA IQTISODIYOT
This work is licensed under a Creative Commons Attribution 4.0 International License.
