SUN’IY INTELLEKT YORDAMIDA O‘QUVCHINING MATEMATIK FIKRLASH TRAYEKTORIYASINI PROGNOZLASH MODELI
Keywords:
Matematik fikrlash, sun’iy intellekt, prognozlash modeli, learning analytics, neyron tarmoq, kognitiv xatti-harakatlar, adaptiv ta’lim, sequence prediction.Abstract
Ushbu tadqiqotda sun’iy intellekt texnologiyalaridan foydalanib o‘quvchilarning matematik fikrlash trayektoriyasini prognozlashga mo‘ljallangan yangi model ishlab chiqildi. Tadqiqotning asosiy maqsadi — o‘quvchining yechim topish jarayonidagi kognitiv xatti-harakatlarini, xatolarni takrorlash ehtimolini, murakkablikka moslashuv darajasini va individual o‘quv sur’atini tahlil qiluvchi AI-algoritm yaratishdir. Metodologiya sifatida neyron tarmoqlar, ketma-ketlikni bashoratlash (sequence prediction), o‘quv faoliyati analitikasi (learning analytics), hamda matematik amallarning mikro-ko‘nikmalarini aniqlashga asoslangan “MinSkill Mapping” texnologiyasi qo‘llandi. 312 nafar o‘quvchidan olingan real yechim jarayonlari (step-by-step logs) asosida model o‘qitilgan va sinovdan o‘tkazilgan.Natijalar shuni ko‘rsatdiki, taklif etilgan prognozlash modeli o‘quvchining keyingi yechim bosqichini aniqlashda 89.4% aniqlik ko‘rsatdi, murakkab masalalarda xatolik yuz berish ehtimolini oldindan belgilashda esa 81.7% samaradorlikka erishdi. Shuningdek, model individual o‘quv yo‘nalishi uchun moslashtirilgan tavsiyalarni shakllantira oldi: masalan, ayrim o‘quvchilarda mantiqiy bog‘lanishlarni qurish qiyinligi yoki algebraik manipulyatsiyalarni bajarishdagi sustlik aniqlanib, avtomatik ravishda personalizatsiya qilingan mashqlar taqdim qilindi.Tadqiqot natijalari sun’iy intellekt yordamida matematik ta’limni differensiallashtirish, o‘quv dasturlarini shaxsga yo‘naltirilgan qilish va matematika fanida adaptiv o‘qitish tizimlarini yaratishda samarali bo‘lishini ko‘rsatadi. Ushbu loyihada ishlab chiqilgan prognozlash modeli O‘zbekiston ta’limi uchun yangicha yondashuv bo‘lib, o‘quvchilarning matematik fikrlash jarayonini chuqur tahlil qilish va real vaqt rejimida nazorat qilish imkonini beradi.
References
1. Brozo, W. (2024). AI-driven personalized learning pathways in mathematics education. Journal of Digital Education, 18(2), 55–72.
2. Chen, L., & Park, J. (2023). Sequence modelling for predicting students’ learning steps in mathematics. Computers & Education, 200, 104815.
3. Feng, Y. (2023). Learning analytics for modeling mathematical cognition: A systematic review. Educational Data Science, 7(1), 44–61.
4. Garcia, R., & Miller, D. (2024). Neural networks for adaptive math learning systems: An empirical study. AI in Education Review, 12(3), 112–129.
5. Garrison, P. (2023). Cognitive analysis of algebraic thinking using artificial intelligence tools. Mathematics Education Research Journal, 45(1), 77–98.
6. Huang, X. (2024). Predictive modelling in STEM learning using LSTM neural networks. IEEE Access, 12, 55441–55455.
7. Khosravi, H. (2024). Artificial intelligence applications in personalized mathematics education. International Journal of STEM Education, 11(2), 1–17.
8. Kim, S., & Choi, H. (2024). Attention-based neural architectures for predicting student thinking patterns. Applied Intelligence, 54(2), 1251–1267.
9. Lee, J. (2023). Adaptive difficulty generation using deep learning in K–12 mathematics. Journal of Learning Systems, 5(4), 301–320.
10. Li, Y. (2024). AI-based cognitive modelling of students’ mathematical behaviour. Journal of Learning Analytics, 10(1), 22–35.
11. Lu, T., & Wang, C. (2024). Fractal pathway analysis in students’ mathematical problem solving. Educational Modelling Journal, 9(2), 88–103.
12. Ma, X. (2023). Deep learning for detecting misconceptions in algebra problem solving. Computers in the Schools, 40(3), 155–173.
13. Miller, K. (2023). Explaining student misconceptions with deep neural networks. Education & Artificial Intelligence, 6(2), 16–29.
14. OECD. (2023). AI and the Future of Education: Opportunities and Challenges. OECD Publishing.
15. PISA. (2022). Mathematics performance, cognitive strategies and learning patterns. OECD.
16. Patel, R., & Gomez, F. (2024). Neuro-symbolic models in modelling mathematical reasoning. Cognitive Computing Journal, 21(1), 77–93.
17. Qiu, X., & Zheng, L. (2024). Big data analysis of student problem-solving behaviours in mathematics. Big Data in Education, 15(3), 624–639.
18. Rahman, A. (2023). AI-enabled diagnosis of learning difficulties in mathematics education. Educational Technology Quarterly, 37(2), 104–122.
19. Sato, M. (2024). Mathematical thinking pathways among secondary school learners: A cognitive analysis. Mathematics Insights, 8(1), 34–58.
20. Shin, D., & Park, E. (2023). Deep learning architectures for modelling students’ sequential behaviour. AI & Society, 38(2), 455–470.
21. UNESCO. (2024). AI Competency Framework for Teachers: Guidelines for Digital Pedagogy. Paris: UNESCO Publishing.
22. Woolf, B. (2023). Artificial intelligence in mathematics instruction: Progress and challenges. ACM Transactions on Learning Technologies, 16(4), 1–19.
23. Xu, L. (2024). Cognitive sequencing in algebra problem solving: A neural network approach. Journal of Mathematical Psychology, 101, 102–118.
24. Yang, K., & Lim, J. (2023). Predictive analytics in digital classrooms: Modelling student trajectories. Journal of Smart Education, 14(3), 201–216.
25. Zhang, H. (2024). Error forecasting for K–12 mathematics learners using deep learning. Computers in the Schools, 41(1), 55–73.
