MASHINANI OʻQITISH ALGORITMI ORQALI MAKTAB O‘QUVCHILARINING PSIXOLOGIK HOLATINI IKKITA SINFGA AJRATISH: STRESS MAVJUD VA STRESS MAVJUD EMAS

Erkaboy Samandarov

Authors

Erkaboy Samandarov Toshkent irrigatsiya va qishloq xoʻjaligini mexanizatsiyalash muhandislari institute

Keywords:

XGBoost, SVM, Random Forest, maktab oquvchisi, psixologik holat

Abstract

Ushbu maqolada maktab o‘quvchilarining psixologik holatini “stress bor” va “stress yo‘q” sinflariga ajratish uchun XGBoost (Extreme Gradient Boosting) masinani o‘rgatish algoritmi asosida klassifikatsiya modeli ko‘rib chiqiladi. Dastlab maqolada qaralayotgan masalaning matematik modeli quriladi. Keyin masala uchun ishlatiladigan model XGBoostning matematik modeli va qaralayotgan masalani yechishni matematik modeli ko‘rib chiqiladi. Maqolada qaralayotgan masala uchun maktab o‘quvchilarining psixologik xususiyatlari asosida ma’lumotlar to‘plami yaratilgan. Pyton dasturlash tilida maqolada qaralayotgan masala uchun dasturiy ta’minot tuzilgan. Maqolada qaralayotgan masala uchun XGBoost regulyarizatsiya gradientlarni optimallashtirish va parallellashgan hisoblash imkoniyatlari ortiqcha moslashuv muammosini samarali yecha oldi. Model qaralayotgan masalani sinflarga ajratish natijalariga qisqacha qaraladigan bo‘lsa, aniqlik (accuracy) 82% tashkil qildi. Bu natija qaralayotgan masala uchun yuqori hisoblanadi. XGBoost Support vector machine (SVM) va tasodifiy ormon mashinani o‘rgatish algoritmlariga solishtirganda yuqori tezlik va aniqlik ko‘rsatkichlari namoyish qildi. Natijalar shuni ko‘rsatadiki, ushbu yondashuv maktab sharoitida real vaqt rejimida maktab o‘quvchilaridagi stressni aniqlash tizimlarini yaratishda kelajakda asosiy vosita bo‘la oladi.

References

Romero C., Ventura S. Educational data mining: A survey from 1995 to 2005 //Expert systems with applications. – 2007. – Т. 33. – №. 1. – С. 135-146.

Romero C., Ventura S. Educational data mining: a review of the state of the art //IEEE Transactions on Systems, Man, and Cybernetics, Part C (applications and reviews). – 2010. – Т. 40. – №. 6. – С. 601-618.

Peña-Ayala A. Educational data mining: A survey and a data mining-based analysis of recent works //Expert systems with applications. – 2014. – Т. 41. – №. 4. – С. 1432-1462.

Samandarov E. The ARCHITECTURE OF EDUCATIONAL PLATFORM BASED ON MACHINE LEARNING //Journal of Mathematics, Mechanics and Computer Science. – 2024. – Т. 124. – №. 4. – С. 86-102.

Holmes W., Tuomi I. State of the art and practice in AI in education //European Journal of Education. – 2022. – Т. 57. – №. 4. – С. 542-570.

Luckin R., Holmes W. Intelligence unleashed: An argument for AI in education. – 2016.

Chen L., Chen P., Lin Z. Artificial intelligence in education: A review //Ieee Access. – 2020. – Т. 8. – С. 75264-75278.

Arnold M. L. et al. A look at the condition of rural education research: Setting a direction for future research //Journal of research in Rural Education. – 2005. – Т. 20. – №. 6. – С. 1-25.

Zeichner K. The new scholarship in teacher education //Educational researcher. – 1999. – Т. 28. – №. 9. – С. 4-15.

Kourilsky M. L., Walstad W. B. Entrepreneurship and female youth: Knowledge, attitudes, gender differences, and educational practices //Journal of Business venturing. – 1998. – Т. 13. – №. 1. – С. 77-88.

Myers G. L. et al. Recommendations for improving serum creatinine measurement: a report from the Laboratory Working Group of the National Kidney Disease Education Program //Clinical chemistry. – 2006. – Т. 52. – №. 1. – С. 5-18.

Asselman A., Khaldi M., Aammou S. Enhancing the prediction of student performance based on the machine learning XGBoost algorithm //Interactive Learning Environments. – 2023. – Т. 31. – №. 6. – С. 3360-3379.

Zopluoglu C. Detecting examinees with item preknowledge in large-scale testing using extreme gradient boosting (XGBoost) //Educational and psychological measurement. – 2019. – Т. 79. – №. 5. – С. 931-961.