JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

OLIY TA’LIM MUASSASALARIDA PROFESSOR-O‘QITUVCHILARNING O‘QUV YUKLAMALARINI KO‘P MEZONLI OPTIMALLASHTIRISHNING MILP VA GENETIK ALGORITMGA ASOSLANGAN GIBRID MODELI

Saidova Fazilat Muzaffarovna1, Saidоv Samandar Muzaffarоvich2

1 Toshkent Amaliy fanlar

2 Muhammad al-Xоrazmiy nоmidagi TATU

Zenodo DOI: 10.5281/zenodo.23318935

Keywords

professor-o‘qituvchi yuklamasi ko‘p mezonli optimallashtirish optimallashtirish modeli Mixed-Integer Linear Programming yuklama balansi constraint programming oliy ta’lim genetik algoritm MILP qarorlarni qo‘llab-quvvatlash tizimi

Abstract

Oliy ta’lim muassasalarida professor-o‘qituvchilarning o‘quv yuklamalarini samarali va muvozanatli taqsimlash ko‘plab cheklovlar, o‘qituvchi–fan mosligi, o‘quv guruhlari soni va mavjud yuklamalarni bir vaqtning o‘zida hisobga olishni talab qiladigan murakkab optimallashtirish masalasidir. Ushbu tadqiqotda professor-o‘qituvchilarning o‘quv yuklamalarini ko‘p mezonli optimallashtirishga mo‘ljallangan gibrid model taklif etiladi. Model constraint-based filtering, Mixed-Integer Linear Programming (MILP), multi-objective optimization va Genetic Algorithm (GA) usullarining integratsiyasiga asoslangan. Dastlab, qat’iy o‘quv jarayoni cheklovlariga mos kelmaydigan taqsimot variantlari chiqarib tashlanadi. Keyingi bosqichda MILP yordamida optimal yoki unga yaqin optimal yechim aniqlanadi va o‘qituvchi–fan mosligi, yuklama balansi hamda oldingi davrga nisbatan o‘zgarish darajasi birgalikda optimallashtiriladi. Katta hajmdagi masalalarda GA qidiruv jarayonining samaradorligini oshirish uchun qo‘llaniladi. Taklif etilayotgan model yuklamalarni avtomatik, muvozanatli va cheklovlarga mos ravishda shakllantirish imkonini beradi. Modelning amaliy samaradorligini universitet o‘quv yuklamalarini boshqarish axborot tizimi ma’lumotlari asosida baholash rejalashtirilgan.

Views: 78 Published: 2026-10-12 Pages: 76-82 Volume: 4 Issue: 5

References

  1. Mobasher B., Cooley R., Srivastava J. Automatic Personalization Based on Web Usage Mining // Communications of the ACM. – 2000. – Vol. 43(8). – P. 142–151.
  2. Burke R. Hybrid Recommender Systems: Survey and Experiments // User Modeling and User-Adapted Interaction. – 2002. – Vol. 12. – P. 331–370.
  3. Yang Y., Pedersen J.O. A Comparative Study on Feature Selection in Text Categorization // Proceedings of ICML. – 1997. – P. 412–420.
  4. Mo‘minov B.B., Saidov S.M. Web resurslarda foydalanuvchi ehtiyojlarini klasterlash asosida aniqlash usullari // Actual Scientific Research in the Modern World. – 2023. – Issue 4(119). – P. 241–244.
  5. O‘zbekiston Respublikasi Prezidentining qarori. “Raqamli iqtisodiyotni rivojlantirish strategiyasi”. – Toshkent, 2020.
  6. Google Scholar ilmiy ma’lumotlar bazasi. https://scholar.google.com
  7. Saidov S.M., Jo‘rayev N.S. Shaxsga yo‘naltirilgan axborot tizimlarida foydalanuvchi profillarini shakllantirish // Zamonaviy axborot texnologiyalari. – Toshkent, 2022. – №3. – B. 45–52.
  8. Aggarwal C.C. Recommender Systems: The Textbook. – Springer, 2016. – 498 p.
  9. ZiyoNET axborot-ta’lim portali. Shaxsga yo‘naltirilgan axborot tizimlari bo‘yicha elektron resurslar. https://www.ziyonet.uz
  10. Li X., Lin T.Y. Mining User Navigation Patterns for Web Personalization // Knowledge-Based Systems. – 2011. – Vol. 24(4). – P. 580–588.
  11. Zhang Y., Pennacchiotti M. Recommender Systems for Personalized Web Search // WWW Conference Proceedings. – 2013. – P. 1029–1038.
  12. Wang J., Zhao Y. Clustering Algorithms in Web Usage Mining // Journal of Information Science. – 2014. – Vol. 40(2). – P. 199–213.
  13. Yang J., Wu H. CLOPE: A Fast and Effective Clustering Algorithm for Transactional Data // Proceedings of ACM SIGKDD. – 2002. – P. 682–687.
  14. Ricci F., Rokach L., Shapira B. Introduction to Recommender Systems Handbook. – Springer, 2015. – 870 p.