<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD with OASIS Tables with MathML3 v1.4 20241031//EN" "https://jats.nlm.nih.gov/archiving/1.4/JATS-archive-oasis-article1-4-mathml3.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" dtd-version="1.4" article-type="research-article" xml:lang="en"><front><journal-meta><journal-title-group><journal-title xml:lang="ru">Математическая физика и компьютерное моделирование</journal-title></journal-title-group><issn publication-format="print">2587-6325</issn><issn publication-format="electronic">2587-6902</issn></journal-meta><article-meta><article-id pub-id-type="doi">10.15688/mpcm.jvolsu.2026.2.4</article-id><article-categories><subj-group><subject>Other</subject></subj-group></article-categories><title-group><article-title xml:lang="ru">СРАВНИТЕЛЬНЫЙ АНАЛИЗ НЕЙРОСЕТЕВЫХ МЕТОДОВ РЕШЕНИЯ МОДЕЛИ ОДИНОЧНОГО ДИСЛОКАЦИОННОГО ИСТОЧНИКА ГЕОАКУСТИЧЕСКОЙ ЭМИССИИ</article-title><trans-title-group xml:lang="en"><trans-title>COMPARATIVE ANALYSIS OF NEURAL NETWORK METHODS FOR SOLVING THE MODEL OF A SINGLE DISLOCATION SOURCE OF GEOACOUSTIC EMISSION</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Сергиенко</surname><given-names>Дарья Фаритовна</given-names></name><name xml:lang="en"><surname>Sergienko</surname><given-names>Darya</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff2"/><xref ref-type="aff" rid="aff3"/><xref ref-type="aff" rid="aff4"/><email>sergienko@ikir.ru</email><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0008-6512-4537</contrib-id></contrib><aff-alternatives id="aff1"><aff><institution xml:lang="en">Institute of Cosmophysical Research and Radio Wave Propagation,</institution><city xml:lang="en">Paratunka</city><country xml:lang="en">Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="en">Far Eastern Branch of the Russian Academy of Sciences; Vitus Bering Kamchatka State University</institution><city xml:lang="en">Petropavlovsk-Kamchatsky</city><country xml:lang="en">Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff3"><aff><institution xml:lang="ru">Институт космофизических исследований и распространения радиоволн ДВО РАН</institution><city xml:lang="ru">Паратунка</city><country xml:lang="ru">Российская Федерация</country></aff></aff-alternatives><aff-alternatives id="aff4"><aff><institution xml:lang="ru">Камчатский государственный университет им. Витуса Беринга</institution><city xml:lang="ru">Петропавловск-Камчатский</city><country xml:lang="ru">Российская Федерация</country></aff></aff-alternatives></contrib-group><pub-date pub-type="epub" iso-8601-date="2026-10-27"><day>27</day><month>10</month><year>2026</year></pub-date><volume>29</volume><issue>2</issue><fpage>53</fpage><lpage>71</lpage><history><date date-type="received" iso-8601-date="2026-04-20"><day>20</day><month>04</month><year>2026</year></date><date date-type="accepted" iso-8601-date="2026-07-27"><day>27</day><month>07</month><year>2026</year></date></history><permissions><license xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:title="CC BY 4.0"><ali:license_ref>https://creativecommons.org/licenses/by/4.0/</ali:license_ref><license-p xml:lang="ru">CC BY 4.0</license-p></license></permissions><self-uri content-type="pdf" xlink:href="publication-cbc17f18-db49-482d-a144-4e810ab01149.pdf" xlink:title="PDF"/><abstract xml:lang="ru"><p>В данной работе представлен сравнительный анализ вычислительных методов для моделирования одиночного дислокационного источника излучения геоакустической эмиссии – осциллятора Берлаге. Используются численный метод Розенброка четвертого порядка точности, параллельная модификация физико-информированной нейронной сети на три субдомена (TriDomainPINN), а также нейронная сеть на основе полиномов Лежандра (LeNN) для решения модели геоакустической эмиссии. Параллельная версия PINN позволяет повысить эффективность построения решения и сократить время обучения за счет декомпозиции области моделирования. Все алгоритмы реализованы на языке Python с использованием библиотеки PyTorch. Применяются механизм ранней остановки обучения сетей и распределение точек коллокации по закону Чебышева. Для каждого метода проведена оценка точности, скорости сходимости и вычислительной эффективности. Численные эксперименты показывают, что полиномиальная сеть Лежандра обеспечивает высокую точность аппроксимации при значительном сокращении вычислительных затрат и времени.</p></abstract><abstract xml:lang="en" abstract-type="summary"><p>This paper presents a comparative analysis of computational methods for modeling a single dislocation source of geoacoustic emission radiation, the Berlage oscillator. The paper considers the Rosenbrock numerical method of the fourth order of accuracy, a parallel modification of a physically informed neural network into three subdomains (TriDomainPINN), as well as a neural network based on Legendre polynomials (LeNN). The parallel version of PINN makes it possible to increase the efficiency of the solution and reduce the learning time by decomposing the modeling area. All algorithms are implemented in Python using the PyTorch library; the implementation provides a mechanism for early stopping of network training and the distribution of collocation points according to Chebyshev’s law. Accuracy, convergence rate, and computational efficiency were evaluated for each method. Numerical experiments show that the Legendre polynomial network provides high approximation accuracy with a significant reduction in computational costs and time.</p></abstract><kwd-group xml:lang="ru"><kwd>полиномиальные нейронные сети</kwd><kwd>PINN</kwd><kwd>MLP</kwd><kwd>LeNN</kwd><kwd>импульс Берлаге</kwd><kwd>ортогональные полиномы</kwd><kwd>машинное обучение</kwd><kwd>аппроксимация сигналов</kwd></kwd-group><kwd-group xml:lang="en"><kwd>polynomial neural networks</kwd><kwd>PINN</kwd><kwd>MLP</kwd><kwd>LeNN</kwd><kwd>Berlage pulse</kwd><kwd>orthogonal polynomials</kwd><kwd>machine learning</kwd><kwd>signal approximation</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено при поддержке государственного задания ИКИР ДВО РАН № 124012300245-2. Тема «Взаимодействие физических процессов в системе ближнего космоса и геосфер» (2024–2028 гг.).</funding-statement></funding-group></article-meta></front><back><ref-list><ref id="ref1"><mixed-citation publication-type="other" xml:lang="ru">Гапеев, М. И. Связанные осцилляторы как модель высокочастотной геоакустической эмиссии / М. И. Гапеев, А. А. Солодчук, Р. И. Паровик // Вестник КРАУНЦ. Физико-математические науки. – 2022. – Т. 40, № 3. – C. 88–100. – DOI: 10.26117/2079-6641-2022-40-3-88-100</mixed-citation></ref><ref id="ref2"><mixed-citation publication-type="other" xml:lang="ru">Кузьмин, Н. М. Эффективность параллельных вычислений гравитационных сил методом TreeCode в моделях N-тел / Н. М. Кузьмин, Д. С. Сиротин, А. В. Хоперсков // Математическая физика и компьютерное моделирование. – 2024. – Т. 27, № 4. – C. 5–18. – DOI: 10.15688/mpcm.jvolsu.2024.4.4</mixed-citation></ref><ref id="ref3"><mixed-citation publication-type="other" xml:lang="ru">Сергиенко, Д. Ф. Сравнение эффективности численных методов и нейросетевого подхода к исследованию математической модели высокочастотной геоакустической эмиссии с одним дислокационным источником / Д. Ф. Сергиенко, Р. И. Паровик // Успехи кибернетики. – 2025. – Т. 6, № 4. – C. 106–113.</mixed-citation></ref><ref id="ref4"><mixed-citation publication-type="other" xml:lang="ru">Сергиенко, Д. Ф. Исследование эффективности численных методов для решения математической модели высокочастотной геоакустической эмиссии / Д. Ф. Сергиенко, Р. И. Паровик // Вестник КРАУНЦ. Физико-математические науки. – 2025. – Т. 50, № 1. – C. 169–183. – DOI: 10.26117/2079-6641-2025-50-1-169-183</mixed-citation></ref><ref id="ref5"><mixed-citation publication-type="other" xml:lang="ru">Сергиенко, Д. Ф. Моделирование высокочастотной геоакустической эмиссии с помощью осциллятора Берлаге / Д. Ф. Сергиенко, Р. И. Паровик // Вестник ДГУ. Серия 1, Естественные науки. – 2025. – Т. 40, № 3. – C. 29–43. – DOI: 10.21779/2542-0321-2025-40-3-29-43</mixed-citation></ref><ref id="ref6"><mixed-citation publication-type="other" xml:lang="ru">Храпов, С. С. Численное моделирование двумерных газодинамических течений в многокомпонентных неравновесных средах / С. С. Храпов // Математическая физика и компьютерное моделирование. – 2025. – Т. 28, № 1. – C. 60–87. – DOI: 10.15688/mpcm.jvolsu.2025.1.5</mixed-citation></ref><ref id="ref7"><mixed-citation publication-type="other" xml:lang="ru">Aziz, A. A. H. A. A Shifted Chebyshev Neural Network Approach for Nonlinear Variable-Order Fractional Differential Equations / A. A. H. A. Aziz, N. Senu, N. E. Zamri // Computational and Applied Mathematics. – 2026. – Vol. 45. – P. 262. – DOI: 10.1007/s40314-026-03650-3</mixed-citation></ref><ref id="ref8"><mixed-citation publication-type="other" xml:lang="ru">Chen, J. Improved Modeling and Generalization Capabilities of Graph Neural Networks with Legendre Polynomials / J. Chen, L. Xu // IEEE Access. – 2023. – Vol. 11. – P. 63442–63450.</mixed-citation></ref><ref id="ref9"><mixed-citation publication-type="other" xml:lang="ru">Grohs, P. Space-time Error Estimates for Deep Neural Network Approximations for Differential Equations / P. Grohs, F. Hornung, A. Jentzen // Advances in Computational Mathematics. – 2023. – Vol. 49, № 4. – P. 1–78. – DOI: 10.1007/s10444-022-09970-2</mixed-citation></ref><ref id="ref10"><mixed-citation publication-type="other" xml:lang="ru">Hendrycks, D. Gaussian Error Linear Units (GELUs) / D. Hendrycks, K. Gimpel // arXiv preprint. – 2016. – P. arXiv:1606.08415.</mixed-citation></ref><ref id="ref11"><mixed-citation publication-type="other" xml:lang="ru">Kaps, P. Rosenbrock Methods Using Few LU-Decompositions Get Access Arrow / P. Kaps, A. Ostermann // Journal of Numerical Analysis. – 1989. – Vol. 9. – P. 15–27. – DOI: 10.1093/imanum/9.1.15</mixed-citation></ref><ref id="ref12"><mixed-citation publication-type="other" xml:lang="ru">Khan, N. A. Application of Legendre Polynomials Based Neural Networks for the Analysis of Heat and Mass Transfer of a Non-Newtonian Fluid in a Porous Channel / N. A. Khan, M. Sulaiman, P. Kumam // Advances in Continuous and Discrete Models. – 2022. – Vol. 2022. – P. 7. – DOI: 10.1186/s13662-022-03676-x</mixed-citation></ref><ref id="ref13"><mixed-citation publication-type="other" xml:lang="ru">DDR-PINN: A Dynamic Domain – Gradient Reweighting Physics-Informed Neural Network / S. Lei, B. Gulnar, C. Yang, N. Kunicina, R. Grants, U. Grunde // Applied Sciences. – 2026. – Vol. 16. – P. 2366. – DOI: 10.3390/app16052366</mixed-citation></ref><ref id="ref14"><mixed-citation publication-type="other" xml:lang="ru">Liu, Z. Neural Network as a Function Approximator and Its Application in Solving Differential Equations / Z. Liu, Y. Yang, Q. Cai // Applied Mathematics and Mechanics (English Edition). – 2019. – Vol. 40. – P. 237–248. – DOI: 10.1007/s10483-019-2429-8</mixed-citation></ref><ref id="ref15"><mixed-citation publication-type="other" xml:lang="ru">Moseley, B. Finite Basis Physics-Informed Neural Networks (FBPINNs): A Scalable Domain Decomposition Approach for Solving Differential Equations / B. Moseley, A. Markham, T. Nissen-Meyer // Advances in Computational Mathematics. – 2023. – Vol. 49. – P. 62. – DOI: 10.1007/s10444-023-10065-9</mixed-citation></ref><ref id="ref16"><mixed-citation publication-type="other" xml:lang="ru">Pao, Y. H. The Functional Link Net and Learning Optimal Control / Y. H. Pao, S. M. Phillips // Neurocomputing. – 1995. – Vol. 9, № 2. – P. 149–164.</mixed-citation></ref><ref id="ref17"><mixed-citation publication-type="other" xml:lang="ru">Parovik, R. Algorithms for Solving Ordinary Differential Equations Based on Orthogonal Polynomial Neural Networks / R. Parovik // Algorithms. – 2026. – Vol. 19. – P. 82. – DOI: 10.3390/a19010082</mixed-citation></ref><ref id="ref18"><mixed-citation publication-type="other" xml:lang="ru">Ponalagusamy, R. A Parallel Fourth Order Rosenbrock Method: Construction, Analysis and Numerical Comparison / R. Ponalagusamy, K. Ponnammal // International Journal of Applied and Computational Mathematics. – 2015. – Vol. 1. – P. 45–68. – DOI: 10.1007/s40819-014-0002-x</mixed-citation></ref><ref id="ref19"><mixed-citation publication-type="other" xml:lang="ru">Sergienko, D. Berlage Oscillator as a Mathematical Model of High-Frequency Geoacoustic Emission with One Dislocation Source / D. Sergienko, R. Parovik // Acoustics. – 2025. – Vol. 7, № 65. – DOI: 10.3390/acoustics7040065</mixed-citation></ref><ref id="ref20"><mixed-citation publication-type="other" xml:lang="ru">Improvement of Methods for Sparse Model Identification of Pulsed Geophysical Signals / A. Tristanov, O. Lukovenkova, Yu. Marapulets, A. Kim // Proceedings of SPA 2019. – 2019. – P. 256–260. – DOI: 10.23919/SPA.2019.8936817</mixed-citation></ref><ref id="ref21"><mixed-citation publication-type="other" xml:lang="ru">A General Method for Solving Differential Equations of Motion Using Physics-Informed Neural Networks / W. Zhang, P. Ni, M. Zhao, X. Du // Applied Sciences. – 2024. – Vol. 14. – P. 7694. – DOI: 10.3390/app14177694</mixed-citation></ref><ref id="ref22"><mixed-citation publication-type="other" xml:lang="ru">Lin, C.-H. Wind Turbine Driving a PM Synchronous Generator Using Novel Recurrent Chebyshev Neural Network Control with the Ideal Learning Rate / C.-H. Lin // Energies. – 2016. – Vol. 9, № 6. – P. 441. – DOI: 10.3390/en9060441</mixed-citation></ref><ref id="ref23"><mixed-citation publication-type="other" xml:lang="ru">Liu, Z. Neural Network as a Function Approximator and its Application in Solving Differential Equations / Z. Liu, Y. Yang, Q. Cai // Appl. Math. Mech.-Engl. Ed. – 2019. – Vol. 40. – P. 237–248. – DOI: https://doi.org/10.1007/s10483-019-2429-8</mixed-citation></ref><ref id="ref24"><mixed-citation publication-type="other" xml:lang="ru">Mostovoy, V. S. Estimation of the Parameters of Seismic Waves / V. S. Mostovoy, S. V. Mostoviy // Reports of the National Academy of Sciences of Ukraine. – 2014. – Vol. 2. – P. 118–123.</mixed-citation></ref><ref id="ref25"><mixed-citation publication-type="other" xml:lang="ru">Mostovoy, V. Optimization of the Dynamic Parameters of an Object in a Mathematical Model of Seismo-Acoustic Monitoring of Natural and Engineering Objects / V. Mostovoy, S. Toliupa, A. Shevchenko // Science-Based Technologies. – 2023. – Vol. 58, № 2. – P. 112. – DOI: 10.18372/2310-5461.58.17647</mixed-citation></ref><ref id="ref26"><mixed-citation publication-type="other" xml:lang="ru">Toliupa, S. Mathematical Model of Physically Realizable Seismic Signals / S. Toliupa // Information Technology and Implementation (IT&amp;Is-2023). – 2023. – P. 126.</mixed-citation></ref><ref id="ref27"><mixed-citation publication-type="other" xml:lang="en">Gapeev M.I., Solodchuk A.A., Parovik R.I. Coupled Oscillators as a Model of High-Frequency Geoacoustic Emission. Vestnik KRAUNTs. Fiziko-matematicheskie nauki, 2022, vol. 40, no. 3, pp. 88-100. DOI: 10.26117/2079-6641-2022-40-3-88-100</mixed-citation></ref><ref id="ref28"><mixed-citation publication-type="other" xml:lang="en">Kuzmin N.M., Sirotin D.S., Khoperskov A.V. Efficiency of Parallel Computations of Gravitational Forces by Treecode Method in N-Body Models. Matematicheskaya fizika i kompyuternoe modelirovanie [Mathematical Models and Computer Simulations], 2024, vol. 27, no. 4, pp. 5-18. DOI: 10.15688/mpcm.jvolsu.2024.4.4</mixed-citation></ref><ref id="ref29"><mixed-citation publication-type="other" xml:lang="en">Sergienko D.F., Parovik R.I. Comparison of Numerical Methods and Neural Network Approaches for Simulating High-Frequency Geoacoustic Emission from a Single Dislocation Source. Uspekhi kibernetiki, 2025, vol. 6, no. 4, pp. 106-113.</mixed-citation></ref><ref id="ref30"><mixed-citation publication-type="other" xml:lang="en">Sergienko D.F., Parovik R.I. Investigation of the Effectiveness of Numerical Methods for Solving a Mathematical Model of High-Frequency Geoacoustic Emission. Vestnik KRAUNTs. Fizikomatematicheskie nauki, 2025, vol. 50, no. 1, pp. 169-183. DOI: 10.26117/2079-6641-2025-50-1-169-183</mixed-citation></ref><ref id="ref31"><mixed-citation publication-type="other" xml:lang="en">Sergienko D.F., Parovik R.I. Modelling of High-Frequency Geoacoustic Emission Using the Berlage Oscillator. Vestnik DGU. Seriya 1, Estestvennye nauki, 2025, vol. 40, no. 3, pp. 29-43. DOI: 10.21779/2542-0321-2025-40-3-29-43</mixed-citation></ref><ref id="ref32"><mixed-citation publication-type="other" xml:lang="en">Khrapov S.S. Numerical Modeling of Two-Dimensional Gas-Dynamic Flows in Multicomponent Nonequilibrium Media. Matematicheskaya fizika i kompyuternoe modelirovanie [Mathematical Models and Computer Simulations], 2025, vol. 28, no. 1, pp. 60-87. DOI: 10.15688/mpcm.jvolsu.2025.1.5</mixed-citation></ref><ref id="ref33"><mixed-citation publication-type="other" xml:lang="en">Aziz A.A.H.A., Senu N., Zamri N.E. A Shifted Chebyshev Neural Network Approach for Nonlinear Variable-Order Fractional Differential Equations. Computational and Applied Mathematics, 2026, vol. 45, pp. 262. DOI: 10.1007/s40314-026-03650-3</mixed-citation></ref><ref id="ref34"><mixed-citation publication-type="other" xml:lang="en">Chen J., Xu L. Improved Modeling and Generalization Capabilities of Graph Neural Networks with Legendre Polynomials. IEEE Access, 2023, vol. 11, pp. 63442-63450.</mixed-citation></ref><ref id="ref35"><mixed-citation publication-type="other" xml:lang="en">Grohs P., Hornung F., Jentzen A. Space-Time Error Estimates for Deep Neural Network Approximations for Differential Equations. Advances in Computational Mathematics, 2023, vol. 49, no. 4, pp. 1-78. DOI: 10.1007/s10444-022-09970-2</mixed-citation></ref><ref id="ref36"><mixed-citation publication-type="other" xml:lang="en">Hendrycks D., Gimpel K. Gaussian Error Linear Units (GELUs). arXiv preprint, 2016, pp. arXiv:1606.08415.</mixed-citation></ref><ref id="ref37"><mixed-citation publication-type="other" xml:lang="en">Kaps P., Ostermann A. Rosenbrock Methods Using Few LU-Decompositions Get Access Arrow. Journal of Numerical Analysis, 1989, vol. 9, pp. 15-27. DOI: 10.1093/imanum/9.1.15</mixed-citation></ref><ref id="ref38"><mixed-citation publication-type="other" xml:lang="en">Khan N.A., Sulaiman M., Kumam P. Application of Legendre Polynomials Based Neural Networks for the Analysis of Heat and Mass Transfer of a Non-Newtonian Fluid in a Porous Channel. Advances in Continuous and Discrete Models, 2022, vol. 2022, pp. 7. DOI: 10.1186/s13662-022-03676-x</mixed-citation></ref><ref id="ref39"><mixed-citation publication-type="other" xml:lang="en">Lei S., Gulnar B., Yang C., Kunicina N., Grants R., Grunde U. DDR-PINN: A Dynamic Domain – Gradient Reweighting Physics-Informed Neural Network. Applied Sciences, 2026, vol. 16, pp. 2366. DOI: 10.3390/app16052366</mixed-citation></ref><ref id="ref40"><mixed-citation publication-type="other" xml:lang="en">Liu Z., Yang Y., Cai Q. Neural Network as a Function Approximator and Its Application in Solving Differential Equations. Applied Mathematics and Mechanics (English Edition), 2019, vol. 40, pp. 237-248. DOI: 10.1007/s10483-019-2429-8</mixed-citation></ref><ref id="ref41"><mixed-citation publication-type="other" xml:lang="en">Moseley B., Markham A., Nissen-Meyer T. Finite Basis Physics-Informed Neural Networks (FBPINNs): A Scalable Domain Decomposition Approach for Solving Differential Equations. Advances in Computational Mathematics, 2023, vol. 49, pp. 62. DOI: 10.1007/s10444-023-10065-9</mixed-citation></ref><ref id="ref42"><mixed-citation publication-type="other" xml:lang="en">Pao Y.H., Phillips S.M. The Functional Link Net and Learning Optimal Control. Neurocomputing, 1995, vol. 9, no. 2, pp. 149-164.</mixed-citation></ref><ref id="ref43"><mixed-citation publication-type="other" xml:lang="en">Parovik R. Algorithms for Solving Ordinary Differential Equations Based on Orthogonal Polynomial Neural Networks. Algorithms, 2026, vol. 19, p. 82. DOI: 10.3390/a19010082</mixed-citation></ref><ref id="ref44"><mixed-citation publication-type="other" xml:lang="en">Ponalagusamy R., Ponnammal K. A Parallel Fourth Order Rosenbrock Method: Construction, Analysis and Numerical Comparison. International Journal of Applied and Computational Mathematics, 2015, vol. 1, pp. 45-68. DOI: 10.1007/s40819-014-0002-x</mixed-citation></ref><ref id="ref45"><mixed-citation publication-type="other" xml:lang="en">Sergienko D., Parovik R. Berlage Oscillator as a Mathematical Model of High-Frequency Geoacoustic Emission with One Dislocation Source. Acoustics, 2025, vol. 7, no. 65. DOI: 10.3390/acoustics7040065</mixed-citation></ref><ref id="ref46"><mixed-citation publication-type="other" xml:lang="en">Tristanov A., Lukovenkova O., Marapulets Yu., Kim A. Improvement of Methods for Sparse Model Identification of Pulsed Geophysical Signals. Proceedings of SPA 2019, 2019, pp. 256-260. DOI: 10.23919/SPA.2019.8936817</mixed-citation></ref><ref id="ref47"><mixed-citation publication-type="other" xml:lang="en">Zhang W., Ni P., Zhao M., Du X. A General Method for Solving Differential Equations of Motion Using Physics-Informed Neural Networks. Applied Sciences, 2024, vol. 14, p. 7694. DOI: 10.3390/app14177694</mixed-citation></ref><ref id="ref48"><mixed-citation publication-type="other" xml:lang="en">Lin C.-H. Wind Turbine Driving a PM Synchronous Generator Using Novel Recurrent Chebyshev Neural Network Control with the Ideal Learning Rate. Energies, 2016, vol. 9, no. 6, p. 441. DOI: 10.3390/en9060441</mixed-citation></ref><ref id="ref49"><mixed-citation publication-type="other" xml:lang="en">Liu Z., Yang Y., Cai Q. Neural Network as a Function Approximator and Its Application in Solving Differential Equations. Appl. Math. Mech.-Engl. Ed., 2019, vol. 40, pp. 237-248. DOI: https://doi.org/10.1007/s10483-019-2429-8</mixed-citation></ref><ref id="ref50"><mixed-citation publication-type="other" xml:lang="en">Mostovoy V.S., Mostoviy S.V. Estimation of the Parameters of Seismic Waves. Reports of the National Academy of Sciences of Ukraine, 2014, vol. 2, pp. 118-123.</mixed-citation></ref><ref id="ref51"><mixed-citation publication-type="other" xml:lang="en">Mostovoy V., Toliupa S., Shevchenko A. Optimization of the Dynamic Parameters of an Object in a Mathematical Model of Seismo-Acoustic Monitoring of Natural and Engineering Objects. Science-Based Technologies, 2023, vol. 58, no. 2, p. 112. DOI: 10.18372/2310-5461.58.17647</mixed-citation></ref><ref id="ref52"><mixed-citation publication-type="other" xml:lang="en">Toliupa S. Mathematical Model of Physically Realizable Seismic Signals. Information Technology and Implementation (IT&amp;Is-2023), 2023, p. 126.</mixed-citation></ref></ref-list></back></article>
