JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

MIKROSKOPIK TASVIRLAR ASOSIDA INFORMATIV BELGILARNI TANLASH VA ZARRACHALARNI TANIB OLISH ALGORITMI

Mamatov Narzullo Solijanovich1, Asqarov Qudrat Azatbayevich1

1 Toshkent irrigatsiya va qishloq xoʻjaligini mexanizatsiyalash muhandislari institute milliy tadqiqot universiteti

Zenodo DOI: 10.5281/zenodo.23948762

Keywords

belgilarni tanlash mashinali o‘qitish tanib olish mikroskopik tasvir havodagi zarrachalar o‘zaro axborot bootstrap mRMR

Abstract

Mazkur maqolada mikroskopik tasvirlardan olingan belgilar to‘plamidan informativ belgilarni tanlash va zarrachalarni tanib olish algoritmi taklif etilgan. Algoritm belgilarni filtrlash, mRMR (maksimal bog‘liqlik, minimal takrorlanish) mezoni bo‘yicha tartiblash va ketma-ket qo‘shish bosqichlaridan iborat bo‘lib, tanlov barqarorligi bootstrap yordamida tekshiriladi. Tanib olishda mayda zarrachalar uchun qisqartirilgan model, ishonchliligi past natijalar uchun esa “noma’lum” sinfi qo‘llaniladi. Tanib olish natijasi asosida zarrachalar massaviy ulushlari va so‘nish koeffitsiyentini baholash tartibi ham taklif etilgan. Algoritm kukun materiallarining 2048 ta sun’iy SEM tasvirida 8 ta namuna sinfini aniqlash masalasida sinovdan o‘tkazildi. Belgilar soni 115 tadan 12 tagacha kamaytirilganda tayanch vektorlar usulining sifati deyarli o‘zgarmadi (macro-F1 0,818 va 0,817). Ishonchlilik chegarasi qo‘llanganda tasvirlarning 70 foizi qabul qilinib, aniqlik 0,817 dan 0,919 gacha oshdi. Olingan natijalar ixcham va talqin qilinadigan belgilar to‘plami bilan yuqori aniqlikka erishish mumkinligini ko‘rsatadi

Views: 55 Published: 2026-10-28 Pages: 94-100 Volume: 4 Issue: 5-Special-Issues

References

  1. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
  2. Pope, C.A., Dockery, D.W. (2006). Health effects of fine particulate air pollution: lines that connect. Journal of the Air & Waste Management Association, 56(6), 709–742.
  3. Peng, H., Long, F., Ding, C. (2005). Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1226–1238.
  4. Chow, C.K. (1970). On optimum recognition error and reject tradeoff. IEEE Transactions on Information Theory, 16(1), 41–46.
  5. Chen, T., Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
  6. DeCost, B.L., Holm, E.A. (2016). A large dataset of synthetic SEM images of powder materials and their ground truth 3D structures. Data in Brief, 9, 727–731.
  7. DeCost, B.L., Holm, E.A. (2017). Characterizing powder materials using keypoint-based computer vision methods. Computational Materials Science, 126, 438–445.
  8. Efron, B., Tibshirani, R.J. (1993). An Introduction to the Bootstrap. New York: Chapman & Hall.
  9. Guyon, I., Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of Machine Learning Research, 3, 1157–1182.
  10. Cortes, C., Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
  11. Meinshausen, N., Bühlmann, P. (2010). Stability selection. Journal of the Royal Statistical Society: Series B, 72(4), 417–473.
  12. Mamatov, N.S., Niyozmatova, N.A., Jalelova, M.M., Samijonov, A.N., Tojiboyeva, Sh.X. (2023). Methods for improving contrast of agricultural images. E3S Web of Conferences, 401, 04020. doi: 10.1051/e3sconf/202340104020
  13. Hinds, W.C. (1999). Aerosol Technology: Properties, Behavior, and Measurement of Airborne Particles. 2nd ed. New York: Wiley.
  14. Mamatov, N.S., Asqarov, Q.A. Mikroskopik tasvirlarda zarrachalarning geometrik, teksturaviy va statistik belgilarini shakllantirish algoritmi. [Jurnal nomi, yil, son, sahifalar].