Vol. 2 No. 8 (2026), Articles
Vol. 2 No. 8 (2026)

A UNIFIED MODEL FOR AI-BASED ADAPTIVE AND SECURE ASSESSMENT SYSTEMS IN TECHNICAL EDUCATION

Articles
Published 2026-04-22
Yuldashev Nodirbek Abdumannob o‘g‘li
Andijon davlat texnika instituti, p.f.f.d PhD
PDF

Keywords

ta'limda sun'iy intellekt; moslashuvchan test; xavfsiz baholash tizimlari; bilimlarni kuzatish; tabiiy tilni qayta ishlash savollarini yaratish; ta'limda kiberxavfsizlik; texnik ta'lim; aqlli repetitorlik tizimlari.

Abstract

Ta'limning tezkor raqamli transformatsiyasi individual o'quvchilar ehtiyojlariga moslasha oladigan va xavfsizlik tahdidlariga qarshi chidamli baholash tizimlariga bo'lgan ehtiyojni oshirdi. Biroq, mavjud yondashuvlar odatda moslashuvchan test va baholash xavfsizligini mustaqil tadqiqot sohalari sifatida ko'rib chiqadi, nomutanosib va optimal bo'lmagan tizim dizaynlari paydo bo'ladi. Ushbu tadqiqot texnik ta'lim kontekstlariga maxsus moslashtirilgan sun’iy intellekt asosidagi moslashuvchan va xavfsiz baholash tizimlari uchun yagona optimallashtirish tizimini taklif qiladi.

Taklif qilingan tizim to‘rtta asosiy komponentni birlashtiradi: (1) transformator arxitekturasidan foydalanadigan tabiiy tilni qayta ishlash asosidagi savollar yaratish moduli; (2) chuqur bilimlarni kuzatishga asoslangan talabalar bilimlarini modellashtirish mexanizmi; (3) Elementlarga javob berish nazariyasiga asoslangan va mashinani o‘rganish bilan takomillashtirilgan moslashuvchan test mexanizmi; va (4) anomaliyalarni aniqlash va xulq-atvor tahlilini o'z ichiga olgan ko'p qatlamli kiberxavfsizlik quyi tizimi. Tizim ko'p maqsadli optimallashtirish muammosi sifatida shakllantirilgan bo'lib, unda baholash aniqligi, xavfsizlikning mustahkamligi va o'quvchilarning ishtiroki birgalikda optimallashtiriladi.

Tadqiqot natijalari shuni ko'rsatadiki, moslashuvchan intellekt va kiberxavfsizlik yagona tizimda samarali ravishda birgalikda optimallashtirilishi mumkin, bu esa texnik ta'limda keyingi avlod intellektual baholash tizimlariga ham nazariy, ham amaliy hissa qo'shadi.

PDF

References

Thompson, K., & Davis, A. (2023). The role of artificial intelligence in maintaining academic integrity: A framework for the future. Assessment & Evaluation in Higher Education, 48(5), 712-729.

[2] Sullivan, M., Kelly, A., & McLaughlan, P. (2023). ChatGPT in higher education: Considerations for academic integrity and student learning. Journal of Applied Learning and Teaching, 6(1), 31-39.

[3] Garcia, R., Falkner, K., & Vitale, J. (2023). AI in educational assessment: Opportunities and challenges. Computers and Education: Artificial Intelligence, 4, 100123.

[4] Williamson, D. M., Xi, X., & Breyer, F. J. (2022). A framework for evaluation and use of automated scoring. Educational Measurement: Issues and Practice, 41(1), 16-29.

[5] Zhang, M., Li, X., & Brown, T. (2025). Integrating large language models with item response theory for next-generation adaptive testing. Educational Technology Research and Development, 73(1), 45-72.

[6] Wang, L., Zhang, H., & Miller, P. (2024). Deep learning-based learner profiling for adaptive assessment in STEM education. International Journal of Artificial Intelligence in Education, 34(2), 445-471.

[7] Rudner, L. M., & Liang, T. (2022). Automated essay scoring and the future of educational assessment. Measurement: Interdisciplinary Research and Perspectives, 20(1), 1-11.

[8] Yamamoto, S., Chen, Y., & Park, H. (2024). Blockchain-verified credentialing for secure digital assessment ecosystems. Journal of Computer Assisted Learning, 40(3), 891-908.