Improving the efficiency of real-time monitoring systems based on forecasting models

  • Tolaniddin Nurmukhamedov Tashkent State Transport University
  • Sherzod Yuldashev Tashkent University of Applied Sciences
  • Oybek Koraboshev Research Institute for the Development of Digital Technologies and Artificial Intelligence
Keywords: optimization, time series, stationarity check, autocorrelation, variance, adequacy, linear regression, decision tree, random forest, gradient boosting, neural networks

Abstract

This article examines ways to enhance the efficiency of real-time monitoring systems using forecasting models. Modern monitoring systems require the analysis of constantly changing data. Therefore, it is necessary to apply advanced algorithms for data prediction and qualitative analysis. Today, effective control of technological processes, industrial equipment, information systems, or service platforms directly depends on the reliability of monitoring systems. This study analyzes factors such as problems arising in real-time monitoring systems, delays in data flow processing, accuracy, and stability. The results of the analysis demonstrate that the use of modern machine learning and artificial intelligence-based prediction algorithms leads to significant improvements in the accuracy, reliability, and responsiveness of monitoring systems.

References

[1] M.X.Xudayberdiyev, O.Z.Qoraboshev, N.M.Alimqulov, SH.I.Yuldashev. Ma’lumotlarni intellektual tahlil qilish asosida favqulodda vaziyatlarga oid axborotlarga ishlov berish. Agro Inform jurnali, №2, 2022 yil. – 86 b.
[2] М.Х.Худайбердиев, О.З.Корабошев. Задачи и алгоритмы интеллектуального анализа чрезвычайных ситуации. «Иқтисодиёт тармоқларининг инновацион ривожланишида ахбороткоммуникация технологияларининг аҳамияти» конференция. ТАТУ, 10-11 март, 2-қисм, 2022 йил. – 445 б.
[3] Ю.И.Журавлёв, В.В.Рязанов, О.В.Сенько. Распознавание. Математические методы. Программная система. Практические применения. Изд. ФАЗИС. Москва 2005 г. – 64 с.
[4] Воронцов К.В. О проблемно-ориентированной оптимизации базисов задач распознавания // ЖВМ и МФ. 1998 Т. 38, № 5. – 870 с.
[5] Камилов М.М., Худайбердиев М.Х. Взаимосвязь алгоритмов частичной прецедентности//Узбекский журнал «Проблемы информатики и энергетики». -Ташкент, 2014. - №3-4. – 12 с.
[6] Xudayberdiyev M.X., Yuldashev SH.I. Yirik xajmdagi axborotlarga ishlov berishda timsollarni aniqlash algoritmlari//«Fan va ta’lim-tarbiyaning dolzarb masalalari» respublika ilmiy-nazariy anjumani. -Nukus, 2019. – 197 b.
[7] Kamilov M., Hudayberdiev M., Khamroev A. Algorithm for the Development of a Training Set that Best Describes the Objects of Recognition// 13th International Symposium “Intelligent Systems” (INTELS’18). Procedia Computer Science 150 (2019), Pp. 116-122. https://doi.org/10.1016/j.procs.2019.02.024.
[8] Kamilov M.M., Xudayberdiyev M.X., Xamroyev A.SH. Timsollarni aniqlash masalasida dekompozitsion modullar kombinatsiyasi// Innovatsion yondashuvlar ilm-fan taraqqiyoti kaliti sifatida: yechimlar va istiqbollar: respublika ilmiy-texnik anjumani. -Jizzax, 2020 yil 8-10 oktabr. – 183 b.
Published
2025-06-30
How to Cite
Nurmukhamedov, T., Yuldashev, S., & Koraboshev, O. (2025). Improving the efficiency of real-time monitoring systems based on forecasting models. Journal of Transport, 2(2), 164-167. https://doi.org/10.56143/jot-journal.v2i2.264
Section
Power Supply, Electric Rolling Stock, Automation and Telemechanics