Yerzhan Malgazhdarov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yerzhan Malgazhdarov has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Almas Temirbekov
Al-Farabi Kazakh National University
3 shared publications - Aigerim Tleulesova
Al-Farabi Kazakh National University; National Engineering Academy of the Republic of Kazakhstan
1 shared publication - Baidaulet Urmashev
Al-Farabi Kazakh National University
1 shared publication - Bekzat Karimkyzy
Department of Information Systems, D. Serikbayev East Kazakhstan Technical University, Ust-Kamenogorsk 070000, Kazakhstan
1 shared publication - Dinara Tamabay
Faculty of Mechanics and Mathematics, Al-Farabi Kazakh National University, Al-Farabi Avenue 71, Almaty 050040, Kazakhstan
1 shared publication - Kubentayeva Saniya
Non-Profit Joint-Stock Company "East Kazakhstan University named after S. Amanzholov
1 shared publication
Latest Publications
- Open Access
- 30 March 2026
- Published by Kazakh University of Technology and Business in Вестник КазУТБ
- Vol. 1 (30)
ENSEMBLING NEURAL NETWORK ARCHITECTURES FOR DIABETES PREDICTION
This article discusses a neural network ensemble algorithm for clinical decision support tasks, using diabetes prediction as an example. Using an ensemble of models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, improves the accuracy and robustness of predictions compared to individual architectures. The Dirichlet Ensemble method, based on the Dirichlet distribution, is used to combine predictions. This method provides flexible and adaptive weighting of results, taking into account the confidence in each model and data uncertainty. Experiments included a comparative analysis of the models' performance, in which RNN demonstrated superior performance in terms of accuracy, recall, and F1 score. The ensemble approach improved the reliability and robustness of predictions, which is critical for clinical decision making and minimizing diagnostic errors. The study confirms the relevance of neural network ensembles and probabilistic fusion methods in medicine, contributing to the development of digital decision support systems. The practical significance of this work lies in the potential for integrating the proposed algorithm into real-world medical information systems to improve the diagnostic quality of diabetes and other chronic diseases. Further research prospects include expanding the ensemble architecture and optimizing the weights using adaptive methods.
- 30 March 2026
- Published by Kazakh University of Technology and Business in Вестник КазУТБ
- Vol. 1 (30)
Open AccessENSEMBLING NEURAL NETWORK ARCHITECTURES FOR DIABETES PREDICTION
This article discusses a neural network ensemble algorithm for clinical decision support tasks, using diabetes prediction as an example. Using an ensemble of models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, improves the accuracy and robustness of predictions compared to individual architectures. The Dirichlet Ensemble method, based on the Dirichlet distribution, is used to combine predictions. This method provides flexible and adaptive weighting of results, taking into account the confidence in each model and data uncertainty. Experiments included a comparative analysis of the models' performance, in which RNN demonstrated superior performance in terms of accuracy, recall, and F1 score. The ensemble approach improved the reliability and robustness of predictions, which is critical for clinical decision making and minimizing diagnostic errors. The study confirms the relevance of neural network ensembles and probabilistic fusion methods in medicine, contributing to the development of digital decision support systems. The practical significance of this work lies in the potential for integrating the proposed algorithm into real-world medical information systems to improve the diagnostic quality of diabetes and other chronic diseases. Further research prospects include expanding the ensemble architecture and optimizing the weights using adaptive methods.
- Open Access
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 32 (3) , 1405-1416
Mathematical and computer modeling of atmospheric air pollutants transformation with input data refinement
This article addresses the critical issue of harmful impurity dispersion in industrial facility atmospheres, considering point sources and factoring in photochemical changes. Conjugate equations are employed to assimilate pollutant data into the transfer equations' right side. Boundary conditions derive from global models like weather research and forecasting (WRF) and system for integrated modeling of atmospheric composition (SILAM), customized for the unique characteristics of an industrial city's pollutants. To encompass anthropogenic heat sources and surface heterogeneity, the model incorporates differential schemes for the atmospheric boundary layer, transport equations, and impurity transformation equations. Parameters for photochemical transformations, varying with weather and time of day, are derived from Ust-Kamenogorsk. A cloud-based geoinformation system (GIS) is developed for monitoring and forecasting air pollution. It assimilates data sources and accounts for photochemical transformations, enabling visualization of diverse weather and environmental scenarios. The article presents numerical modeling results of impurity spread and transformation influenced by mesometeorological processes, topography, and water resources within a specific city.
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 32 (3) , 1405-1416
Open AccessMathematical and computer modeling of atmospheric air pollutants transformation with input data refinement
This article addresses the critical issue of harmful impurity dispersion in industrial facility atmospheres, considering point sources and factoring in photochemical changes. Conjugate equations are employed to assimilate pollutant data into the transfer equations' right side. Boundary conditions derive from global models like weather research and forecasting (WRF) and system for integrated modeling of atmospheric composition (SILAM), customized for the unique characteristics of an industrial city's pollutants. To encompass anthropogenic heat sources and surface heterogeneity, the model incorporates differential schemes for the atmospheric boundary layer, transport equations, and impurity transformation equations. Parameters for photochemical transformations, varying with weather and time of day, are derived from Ust-Kamenogorsk. A cloud-based geoinformation system (GIS) is developed for monitoring and forecasting air pollution. It assimilates data sources and accounts for photochemical transformations, enabling visualization of diverse weather and environmental scenarios. The article presents numerical modeling results of impurity spread and transformation influenced by mesometeorological processes, topography, and water resources within a specific city.
- Open Access
- 8 September 2021
- Published by al-Farabi Kazakh National University in Journal of Mathematics, Mechanics and Computer Science
- Vol. 109 (1) , 63-75
Parallel CUDA implementation of the algorithm for solving the Navier-Stokes equations using the fictitious domain method
An important direction in the development of numerical simulation methods is the study of approximate methods for solving problems of mathematical physics in complex multidimensional fields. To solve many applied problems in irregular areas, the method of fictitious areas is widely used, which is characterized by a high degree of automation of programming. The main idea of the method of fictitious domains is that the problem is solved not in the original complex domain, but in some other, simpler domain. This allows you to create software immediately for a fairly wide class of problems with arbitrary computational domains. The possibilities of applying the method of fictitious domains to the problems of hydrodynamics in the variables “stream function, velocity vortex” have been considered in many works. In this paper, we study a numerical method for solving the Navier-Stokes equations in doubly connected domains. To solve the two-dimensional Navier-Stokes equations in irregular domains, an approximate method based on the method of fictitious domains is proposed. A computational finite difference algorithm for solving an auxiliary problem of the method of fictitious domains has been developed. The results of numerical simulation of two-dimensional Navier-Stokes equations by the method of fictitious domains with continuation by the lowest coefficient are presented. For this problem, a parallel algorithm was developed using CUDA technologies, which was tested on various mesh dimensions
- 8 September 2021
- Published by al-Farabi Kazakh National University in Journal of Mathematics, Mechanics and Computer Science
- Vol. 109 (1) , 63-75
Open AccessParallel CUDA implementation of the algorithm for solving the Navier-Stokes equations using the fictitious domain method
An important direction in the development of numerical simulation methods is the study of approximate methods for solving problems of mathematical physics in complex multidimensional fields. To solve many applied problems in irregular areas, the method of fictitious areas is widely used, which is characterized by a high degree of automation of programming. The main idea of the method of fictitious domains is that the problem is solved not in the original complex domain, but in some other, simpler domain. This allows you to create software immediately for a fairly wide class of problems with arbitrary computational domains. The possibilities of applying the method of fictitious domains to the problems of hydrodynamics in the variables “stream function, velocity vortex” have been considered in many works. In this paper, we study a numerical method for solving the Navier-Stokes equations in doubly connected domains. To solve the two-dimensional Navier-Stokes equations in irregular domains, an approximate method based on the method of fictitious domains is proposed. A computational finite difference algorithm for solving an auxiliary problem of the method of fictitious domains has been developed. The results of numerical simulation of two-dimensional Navier-Stokes equations by the method of fictitious domains with continuation by the lowest coefficient are presented. For this problem, a parallel algorithm was developed using CUDA technologies, which was tested on various mesh dimensions
- 12 June 2021
- Published by National Academy of Sciences of the Republic of Kazakshtan in NEWS OF THE NATIONAL ACADEMY OF SCIENCES OF THE REPUBLIC OF KAZAKHSTAN
- Vol. 3 (337) , 128-137
FICTITIOUS DOMAIN METHOD FOR THE NAVIER-STOKES EQUATIONS
The paper is devoted to the study and mathematical justification of the fictitious domain method for the Navier-Stokes equations. The method of fictitious domain with continuation by the lowest coefficients for the Navier-Stokes equations is substantiated in the work. The theorem of unambiguous solvability of the initial boundary value problem and the existence and uniqueness of the generalized solution of the auxiliary problem for the Navier-Stokes equations in the case of two spatial variables is proved. A numerical implementation of the proposed method of fictitious domain with continuation by the lowest coefficients for the Navier-Stokes equations is carried out. Various graphical illustrations of the results of numerical simulation using the fictitious domain method for the Navier-Stokes equations are presented.
- 12 June 2021
- Published by National Academy of Sciences of the Republic of Kazakshtan in NEWS OF THE NATIONAL ACADEMY OF SCIENCES OF THE REPUBLIC OF KAZAKHSTAN
- Vol. 3 (337) , 128-137
FICTITIOUS DOMAIN METHOD FOR THE NAVIER-STOKES EQUATIONS
The paper is devoted to the study and mathematical justification of the fictitious domain method for the Navier-Stokes equations. The method of fictitious domain with continuation by the lowest coefficients for the Navier-Stokes equations is substantiated in the work. The theorem of unambiguous solvability of the initial boundary value problem and the existence and uniqueness of the generalized solution of the auxiliary problem for the Navier-Stokes equations in the case of two spatial variables is proved. A numerical implementation of the proposed method of fictitious domain with continuation by the lowest coefficients for the Navier-Stokes equations is carried out. Various graphical illustrations of the results of numerical simulation using the fictitious domain method for the Navier-Stokes equations are presented.