REGULATOR OF PARAMETERS OF NON-STATIONARY OBJECTS BASED ON HYBRID MODELS OF NEURAL NETWORK LEARNING OPTIMIZATION
Keywords:
non-stationary objects, identification, optimization, neural network, neuro-fuzzy network, genetic algorithmAbstract
The problem of improving existing and developing new methods and algorithms for data mining based on the combination of dynamic models, neural network, neuro-fuzzy network, genetic algorithms for identifying non-stationary objects is formulated and solved. The developed mechanisms are aimed at obtaining tools that can significantly improve the accuracy of data analysis and processing, the stability of neural network training algorithms with the least time costs. Simplified search procedures and mechanisms for setting parameters using genetic algorithms are implemented to optimize network learning.
References
Jumanov, I. I., & Xolmonov, S. M. (2021, February). Optimization of identification of non-stationary objects due to information properties and features of models. In IOP Conference Series: Materials Science and Engineering (Vol. 1047, No. 1, p. 012064). IOP Publishing.
Jumanov, I. I., & Kholmonov, S. M. (2020). Optimization of identification under the conditions of low reliability of information and parametric uncertainty of non-stationary objects. Chemical Technology, Control and Management, 2020(5), 104-112.
Makhmudovich, K. S., & Sobirjon o’g’li, S. V. (2022). Intellectualization of Data Processing of Non-Stationary Objects in a Complex Problem Environment. EUROPEAN JOURNAL OF INNOVATION IN NONFORMAL EDUCATION, 2(2), 364-368.
Israilovich, D. O., Makhmudovich, K. S., & Uktomovich, Y. F. (2021). Increasing The Credibility Of Forecasting Random Time Series Based On Fuzzy Inference Algorithms. International Journal of Progressive Sciences and Technologies, 26(1), 12-15.
Djumanov, O. I., Kholmonov, S. M., & Ganiev, J. M. (2021). Optimization of data processing based on neural networks and properties of non-stationary objects. Theoretical & Applied Science, (4), 165-168.
Djumanov, O. I., Kholmonov, S. M., & Shukurov, L. E. (2021). Optimization of the credibility of information processing based on hyper semantic document search. Theoretical & Applied Science, (4), 161-164.
Ibragimovich, J. I., Isroilovich, D. O., & Maxmudovich, X. S. (2020, November). Effective recognition of pollen grains based on parametric adaptation of the image identification model. In 2020 International Conference on Information Science and Communications Technologies (ICISCT) (pp. 1-5). IEEE.
Джуманов, О. И., & Холмонов, С. М. (2009). Алгоритмы контроля погрешностей сглаживания при обучении нейросетевых систем обработки данных нестационарной природы. Актуальные проблемы современной науки, (6), 185-190.
Холмонов, С. М., & Облакулов, С. М. (2019). Программный комплекс идентификации временных рядов для прогнозирования нестационарных объектов. Наука и мир, 2(5), 72-74.
Ахатов, А. Р., & Холмонов, С. М. (2018). Повышение достоверности передачи и обработки временного ряда путем фильтрации нестационарных составляющих. Проблемы вычислительной и прикладной математики, (1), 90-99.
Жуманов, И. И., Холмонов, С. М., & Каюмова, Н. (2018). Повышение достоверности обработки данных нестационарных объектов на основе применения мультиконтекстных рекуррентных нейронных сетей. Наука и мир, 1(3), 52-54.
Jumanov, I. I., & Xolmonov, S. M. (2018). Optimization of data processing based on accounting for factors of external expenses, regulation and correction of variables. Chemical Technology, Control and Management, 2018(4), 54-61.
Жуманов, И. И., & Холмонов, С. М. (2011). Оптимизация обучения нейросетевой системы обработки данных на основе статистических свойств информации. Проблемы информатики и энергетики, (3), 50-56.
Makhmudovich, K. S., & Ismoilovich, N. A. . (2022). Increasing the Reliability of Texts of Electronic Documents Based on Soft Calculations under Parametric Uncertainty. Middle European Scientific Bulletin, 21, 126-132. Retrieved from https://cejsr.academicjournal.io/index.php/journal/article/view/1072
Makhmudovich, K. S., & qizi, M. G. M. (2022). Optimization of Data Processing of Non-Stationary Processes Based on Setting the Parameters of Fuzzy Models. International Journal of Human Computing Studies, 4(2), 36-42. Retrieved from https://journals.researchparks.org/index.php/IJHCS/article/view/2723
Djumanov, O. I., & Kholmonov, S. M. (2016). The modified model of training of neural networks in computer industrial systems with modules for nonstationary objects images processing. Control and Management. South Korea, Seoul-Uzbekistan. Tashkent, (5), 54-58.
Djumanov, O., & Kholmonov, S. (2012). Methods and algorithms of selection the informative attributes in systems of adaptive data processing for analysis and forecasting. Applied Technologies & Innovations, 8(3).
This research platform of the Integration of science, education and practice. Scientific-methodical journal in cooperation with the local and international agencies of the sector.