Saida Tastanova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Saida Tastanova has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Saltanbek Mukhambetzhanov
Department of Computer Science, Al-Farabi Kazakh National University, 71 al-Farabi Avenue, Almaty 050040, Kazakhstan
3 shared publications - Dagmawi Lemma Gobena
Department of Computer Science, Addis Ababa University, Addis Ababa P.O. Box 1176, Ethiopia
2 shared publications - Fakhriddin Nuraliev
Tashkent University of Information Technologies named after Muhammad al-Khwarizmi
2 shared publications - Oybek Mirzaevich Narzulloev
Department of Immersive Convergence Content, Kwangwoon University, Seoul, Republic of Korea
2 shared publications - Samson Dawit Bekele
Department of Computer Science, Al-Farabi Kazakh National University, 71 al-Farabi Avenue, Almaty 050040, Kazakhstan
2 shared publications - Timur Imankulov
Faculty of Information Technology, Department of Computer Science, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
2 shared publications
Latest Publications
- Open Access
- 7 October 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (10) , 342
Separating Artificial-Viscosity Annealing from the L-BFGS Viscosity in Physics-Informed Neural Networks for Two-Phase Flow
Physics-informed neural networks (PINNs) remain difficult to train for hyperbolic conservation laws. Artificial viscosity is a common remedy, and several methods reduce its coefficient during training. We examine adaptive moment estimation (Adam) followed by limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) optimisation. The schedule followed during Adam, the viscosity used during L-BFGS, and the checkpoint supplied between them can change together. We separate these factors for the one-dimensional Buckley–Leverett equation using a fixed multilayer perceptron with hyperbolic-tangent activations and 15 paired seeds per configuration. The central experiments impose a zero-diffusive-flux outlet condition. Lowering the L-BFGS viscosity from to increased full-grid relative error by . The schedule–viscosity interaction was and was not detected after multiplicity adjustment. A decay ending at improved on the tested low-endpoint decay before high-viscosity polishing, while its difference from constant high viscosity remained inconclusive. The higher of the two tested constant viscosities improved aggregate and pre-breakthrough accuracy but increased post-breakthrough error. Stage-matched curricula showed no detected accuracy advantage; their greater executed cost arose from intermediate diagnostic L-BFGS phases whose states were discarded. These results identify the terminal viscosity, checkpoint rule, outlet treatment, and optimiser exposure as controls needed to interpret schedule comparisons in this pipeline.- 7 October 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (10) , 342
Open AccessSeparating Artificial-Viscosity Annealing from the L-BFGS Viscosity in Physics-Informed Neural Networks for Two-Phase Flow
Physics-informed neural networks (PINNs) remain difficult to train for hyperbolic conservation laws. Artificial viscosity is a common remedy, and several methods reduce its coefficient during training. We examine adaptive moment estimation (Adam) followed by limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) optimisation. The schedule followed during Adam, the viscosity used during L-BFGS, and the checkpoint supplied between them can change together. We separate these factors for the one-dimensional Buckley–Leverett equation using a fixed multilayer perceptron with hyperbolic-tangent activations and 15 paired seeds per configuration. The central experiments impose a zero-diffusive-flux outlet condition. Lowering the L-BFGS viscosity from to increased full-grid relative error by . The schedule–viscosity interaction was and was not detected after multiplicity adjustment. A decay ending at improved on the tested low-endpoint decay before high-viscosity polishing, while its difference from constant high viscosity remained inconclusive. The higher of the two tested constant viscosities improved aggregate and pre-breakthrough accuracy but increased post-breakthrough error. Stage-matched curricula showed no detected accuracy advantage; their greater executed cost arose from intermediate diagnostic L-BFGS phases whose states were discarded. These results identify the terminal viscosity, checkpoint rule, outlet treatment, and optimiser exposure as controls needed to interpret schedule comparisons in this pipeline. - Open Access
- 2 October 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (19) , 3575
Identifiability and Conditioning of Flux-Parameter Inversion for the Buckley–Leverett Equation
We analyse inversion of the viscosity ratio M in the Buckley–Leverett equation, distinguishing structural identifiability, observation-operator conditioning, and numerical estimation error. The Riemann solution gives from the shock speed s, with relative condition number , which diverges as . The continuum physics objective admits exact solution–parameter pairs for every , so identifying the true ratio requires observations. We examine numerical recovery using a viscous physics-informed neural network (PINN) with positive parameterisation and 30 paired repetitions per setting. At , the median parameter error decreases from without observations to with 25 noisy observations. Additional data decrease the median field error, while median parameter errors are nonmonotone. Over , decreases from to , whereas the smooth-branch Cramér–Rao relative scale for 50 scattered observations with Gaussian noise levels off near . Shock crossings supply additional nonregular information. Finite-network physics losses remain small across the tested ratios, with different orderings on training and held-out points. Scalar controls assess finite-resolution viscous-model discrepancy; complementary PINN tests show poorer recovery as the front sharpens. Recovery accuracy therefore depends jointly on the observation operator, regularisation, and numerical estimator.- 2 October 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (19) , 3575
Open AccessIdentifiability and Conditioning of Flux-Parameter Inversion for the Buckley–Leverett Equation
We analyse inversion of the viscosity ratio M in the Buckley–Leverett equation, distinguishing structural identifiability, observation-operator conditioning, and numerical estimation error. The Riemann solution gives from the shock speed s, with relative condition number , which diverges as . The continuum physics objective admits exact solution–parameter pairs for every , so identifying the true ratio requires observations. We examine numerical recovery using a viscous physics-informed neural network (PINN) with positive parameterisation and 30 paired repetitions per setting. At , the median parameter error decreases from without observations to with 25 noisy observations. Additional data decrease the median field error, while median parameter errors are nonmonotone. Over , decreases from to , whereas the smooth-branch Cramér–Rao relative scale for 50 scattered observations with Gaussian noise levels off near . Shock crossings supply additional nonregular information. Finite-network physics losses remain small across the tested ratios, with different orderings on training and held-out points. Scalar controls assess finite-resolution viscous-model discrepancy; complementary PINN tests show poorer recovery as the front sharpens. Recovery accuracy therefore depends jointly on the observation operator, regularisation, and numerical estimator. - Open Access
- 25 September 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (10) , 829
Adaptive Grid Generation by Solving the Two-Dimensional Diffusion Equation Using Physics-Informed Neural Networks
Adaptive computational grids improve the accuracy and efficiency of numerical simulations by concentrating nodes in regions of particular interest, but classical adaptation methods based on differential equations are often computationally expensive and geometry-dependent. This study proposes a physics-informed neural network (PINN) framework for generating two-dimensional structured adaptive grids by solving the diffusion equation directly, with grid density governed by a prescribed control function. Two neural architectures were developed and compared: a classical PINN, in which boundary conditions are enforced softly through an additional loss term, and a modified PINN (MPINN), in which Dirichlet boundary conditions are embedded exactly into the network architecture using an approximate distance function (ADF) mask. Both methods were tested on two adaptation scenarios—concentration at a single point and concentration along a line segment—and validated against a reference grid obtained by a finite-difference scheme. The MPINN model reduced the mean root-mean-square error by a factor of between 1.4 and 2.0, depending on the adaptation case, together with improved boundary agreement, symmetry, and interval uniformity. Two further configurations with control functions of a more complex shape, a T-shaped junction and a curve of diagonal sine form, were examined together with a variant in which the boundary nodes are allowed to slide along the boundary while the boundary itself is preserved exactly. In these configurations the classical PINN fails to preserve the domain, whereas both mask-based variants reproduce it by construction. The results demonstrate that embedding boundary conditions architecturally, rather than penalizing their violation in the loss function, substantially improves the accuracy and reliability of PINN-based adaptive grid generation.
- 25 September 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (10) , 829
Open AccessAdaptive Grid Generation by Solving the Two-Dimensional Diffusion Equation Using Physics-Informed Neural Networks
Adaptive computational grids improve the accuracy and efficiency of numerical simulations by concentrating nodes in regions of particular interest, but classical adaptation methods based on differential equations are often computationally expensive and geometry-dependent. This study proposes a physics-informed neural network (PINN) framework for generating two-dimensional structured adaptive grids by solving the diffusion equation directly, with grid density governed by a prescribed control function. Two neural architectures were developed and compared: a classical PINN, in which boundary conditions are enforced softly through an additional loss term, and a modified PINN (MPINN), in which Dirichlet boundary conditions are embedded exactly into the network architecture using an approximate distance function (ADF) mask. Both methods were tested on two adaptation scenarios—concentration at a single point and concentration along a line segment—and validated against a reference grid obtained by a finite-difference scheme. The MPINN model reduced the mean root-mean-square error by a factor of between 1.4 and 2.0, depending on the adaptation case, together with improved boundary agreement, symmetry, and interval uniformity. Two further configurations with control functions of a more complex shape, a T-shaped junction and a curve of diagonal sine form, were examined together with a variant in which the boundary nodes are allowed to slide along the boundary while the boundary itself is preserved exactly. In these configurations the classical PINN fails to preserve the domain, whereas both mask-based variants reproduce it by construction. The results demonstrate that embedding boundary conditions architecturally, rather than penalizing their violation in the loss function, substantially improves the accuracy and reliability of PINN-based adaptive grid generation.
- Open Access
- 26 March 2026
- Published by al-Farabi Kazakh National University in Journal of problems in computer science and information technologies
- Vol. 4 (1)
THREE-DIMENSIONAL FRACTAL GEOMETRY MODELING AND DIGITAL HOLOGRAPHY BASED ON R-FUNCTIONS
This paper is devoted to modern research in the field of digital modeling of complex-shaped geometric objects and the determination of their optical properties, which currently represent one of the most relevant challenges in contemporary science. In particular, the problem of realistic representation of three-dimensional objects with fractal geometry and their holographic reconstruction in a full 3D format is of significant scientific and practical importance for such fields as industry, medicine, engineering, architecture, materials science, virtual reality (VR), and digital art. Fractal structures possess a number of unique properties, including self-similarity, unlimited detail, and high spatial complexity, which makes them an effective mathematical basis for modeling natural objects such as plants, vascular systems, bone tissues, crystalline structures, and surface reliefs. At the same time, the geometric representation of fractal forms using classical methods is challenging, and their mathematical modeling requires the application of high-precision and formally rigorous techniques. At present, the mathematical description of fractal objects is often based on statistical, stochastic, or iterative algorithms. However, such approaches are generally characterized by insufficient analytical rigor and smoothness, blurred boundaries, and the lack of a holistic spatial description. In this regard, there arises a need to develop methods for modeling complex fractal forms based on strict analytical expressions, in particular using the R-functions apparatus. An additional challenging task is the reconstruction of holographic images of the modeled fractal objects, which requires high-precision optical modeling. The application of holographic technologies based on the principles of interference and diffraction makes it possible to adequately reproduce the spatial and structural features of fractal objects in a digital environment.
- 26 March 2026
- Published by al-Farabi Kazakh National University in Journal of problems in computer science and information technologies
- Vol. 4 (1)
Open AccessTHREE-DIMENSIONAL FRACTAL GEOMETRY MODELING AND DIGITAL HOLOGRAPHY BASED ON R-FUNCTIONS
This paper is devoted to modern research in the field of digital modeling of complex-shaped geometric objects and the determination of their optical properties, which currently represent one of the most relevant challenges in contemporary science. In particular, the problem of realistic representation of three-dimensional objects with fractal geometry and their holographic reconstruction in a full 3D format is of significant scientific and practical importance for such fields as industry, medicine, engineering, architecture, materials science, virtual reality (VR), and digital art. Fractal structures possess a number of unique properties, including self-similarity, unlimited detail, and high spatial complexity, which makes them an effective mathematical basis for modeling natural objects such as plants, vascular systems, bone tissues, crystalline structures, and surface reliefs. At the same time, the geometric representation of fractal forms using classical methods is challenging, and their mathematical modeling requires the application of high-precision and formally rigorous techniques. At present, the mathematical description of fractal objects is often based on statistical, stochastic, or iterative algorithms. However, such approaches are generally characterized by insufficient analytical rigor and smoothness, blurred boundaries, and the lack of a holistic spatial description. In this regard, there arises a need to develop methods for modeling complex fractal forms based on strict analytical expressions, in particular using the R-functions apparatus. An additional challenging task is the reconstruction of holographic images of the modeled fractal objects, which requires high-precision optical modeling. The application of holographic technologies based on the principles of interference and diffraction makes it possible to adequately reproduce the spatial and structural features of fractal objects in a digital environment.
- 11 April 2023
- Published by Springer Nature
- p. 575-585
Optimization of Fractal Structure Pattern Colors in Carpet Design Using Genetic Algorithm
- 11 April 2023
- Published by Springer Nature
- p. 575-585
Optimization of Fractal Structure Pattern Colors in Carpet Design Using Genetic Algorithm
- Open Access
- 30 October 2022
- Published by Bilingual Publishing Group in Journal of Computer Science Research
- Vol. 4 (4) , 7-14
Сomputational Experience Optimization of Colors in Complex Fractal Images in Carpet Design Using the Simplex Method
Сomputational Experience Optimization of Colors in Complex Fractal Images in Carpet Design Using the Simplex Method
- 30 October 2022
- Published by Bilingual Publishing Group in Journal of Computer Science Research
- Vol. 4 (4) , 7-14
Open AccessСomputational Experience Optimization of Colors in Complex Fractal Images in Carpet Design Using the Simplex Method
Сomputational Experience Optimization of Colors in Complex Fractal Images in Carpet Design Using the Simplex Method