Maksym Sarana
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Maksym Sarana has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Galyna Kriukova
National University of Kyiv-Mohyla Academy
2 shared publications Andrii Cheredachuk
National University of Kyiv-Mohyla Academy, Kyiv, Ukraine
1 shared publicationAndrii Cheredarchuk
National University of Kyiv-Mohyla Academy, Kyiv, Ukraine
1 shared publicationAndrii Malenko
National University of Kyiv-Mohyla Academy, Kyiv, Ukraine
1 shared publication- Oleksandr Sudakov
Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
1 shared publication Oleksii Kashpirovskyi
National University of Kyiv-Mohyla Academy, Kyiv, Ukraine
1 shared publication
Latest Publications
- Open Access
- 22 December 2025
- Published by National University of Kyiv - Mohyla Academy in Mohyla Mathematical Journal
- Vol. 8
PINN-based machine learning for modeling internal waves in semi-infinite fluids
This study investigates the application of Physics-Informed Neural Networks (PINNs) for modeling wave processes at the interface between two incompressible fluids of differing densities. As a first step, the linear formulation of the problem is considered, which admits an analytical solution based on a spectral method involving Fourier decomposition of the initial perturbation. This solution serves as a benchmark for testing and validating the accuracy of the PINN predictions.The implementation is carried out in Python using specialized libraries such as TensorFlow, NumPy, SciPy, and Matplotlib, which provide both efficient deep learning frameworks and tools for solving mathematical physics problems numerically. The approach integrates artificial intelligence with domain-specific knowledge in hydrodynamics, enabling the construction of interpretable and physically consistent models. Particular attention is given to the organization of the computational experiment, automation of visualizations, and storage of intermediate results for further analysis. The PINN model includes a loss function that encodes the governing equations and boundary conditions, and the training is conducted on randomly sampled points across the spatio-temporal domain. The influence of network architecture and training parameters on solution accuracy is examined. Visualization of loss function evolution and predicted wave profiles provides insight into convergence behavior and physical plausibility of the solutions.A comparative analysis between the PINN-based and analytical solutions across different time instances is presented, revealing phase shifts and amplitude deviations. The model demonstrates good agreement at early times and a gradual accumulation of errors as time progresses—an expected feature of this class of methods. The results confirm the feasibility of applying the PINN framework to linear hydrodynamic problems, laying the groundwork for future extensions to weakly and strongly nonlinear regimes, including studies of wave stability and nonlinear wave dynamics.
- 22 December 2025
- Published by National University of Kyiv - Mohyla Academy in Mohyla Mathematical Journal
- Vol. 8
Open AccessPINN-based machine learning for modeling internal waves in semi-infinite fluids
This study investigates the application of Physics-Informed Neural Networks (PINNs) for modeling wave processes at the interface between two incompressible fluids of differing densities. As a first step, the linear formulation of the problem is considered, which admits an analytical solution based on a spectral method involving Fourier decomposition of the initial perturbation. This solution serves as a benchmark for testing and validating the accuracy of the PINN predictions.The implementation is carried out in Python using specialized libraries such as TensorFlow, NumPy, SciPy, and Matplotlib, which provide both efficient deep learning frameworks and tools for solving mathematical physics problems numerically. The approach integrates artificial intelligence with domain-specific knowledge in hydrodynamics, enabling the construction of interpretable and physically consistent models. Particular attention is given to the organization of the computational experiment, automation of visualizations, and storage of intermediate results for further analysis. The PINN model includes a loss function that encodes the governing equations and boundary conditions, and the training is conducted on randomly sampled points across the spatio-temporal domain. The influence of network architecture and training parameters on solution accuracy is examined. Visualization of loss function evolution and predicted wave profiles provides insight into convergence behavior and physical plausibility of the solutions.A comparative analysis between the PINN-based and analytical solutions across different time instances is presented, revealing phase shifts and amplitude deviations. The model demonstrates good agreement at early times and a gradual accumulation of errors as time progresses—an expected feature of this class of methods. The results confirm the feasibility of applying the PINN framework to linear hydrodynamic problems, laying the groundwork for future extensions to weakly and strongly nonlinear regimes, including studies of wave stability and nonlinear wave dynamics.
- 1 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Adaptive Algorithm for Radar-System Parameters Tuning by means of Motion Zone Estimation
This paper focuses on development of algorithm for parameters tuning for Doppler radar-based sensing systems for motion monitoring. The algorithm adapts parameters for better system performance according to estimated motion zone, i.e. mean and maximum distance to objects and their velocities. A new approach for determination of radar height position and tilt angle is proposed and experimentally tested.The method uses radar measurement points cloud only and may be applied for optimization of distance and velocity ranges and reduction of artifacts. Error of tilt angle estimation is 0.7-1.6 degrees in range of 0-45 degrees. Height estimation error depends on moving object height and is less than 1 m. Main goal of the algorithm is estimation of motion zone and corresponding adaptive change of radar-system configuration parameters for optimising system's field of view and performance. The proposed approach may be used for indoor and outdoor motion detection and activity classification in applications such as health diagnostics, health monitoring, surveillance, occupancy sensing, and automotive.
- 1 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Adaptive Algorithm for Radar-System Parameters Tuning by means of Motion Zone Estimation
This paper focuses on development of algorithm for parameters tuning for Doppler radar-based sensing systems for motion monitoring. The algorithm adapts parameters for better system performance according to estimated motion zone, i.e. mean and maximum distance to objects and their velocities. A new approach for determination of radar height position and tilt angle is proposed and experimentally tested.The method uses radar measurement points cloud only and may be applied for optimization of distance and velocity ranges and reduction of artifacts. Error of tilt angle estimation is 0.7-1.6 degrees in range of 0-45 degrees. Height estimation error depends on moving object height and is less than 1 m. Main goal of the algorithm is estimation of motion zone and corresponding adaptive change of radar-system configuration parameters for optimising system's field of view and performance. The proposed approach may be used for indoor and outdoor motion detection and activity classification in applications such as health diagnostics, health monitoring, surveillance, occupancy sensing, and automotive.
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 620-623
Towards Image Processing Based on System of Difference Equations
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 620-623
Towards Image Processing Based on System of Difference Equations