<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2024-24-1-156-164</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-93</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>МАТЕМАТИЧЕСКОЕ И КОМПЬЮТЕРНОЕ МОДЕЛИРОВАНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>MODELING AND SIMULATION</subject></subj-group></article-categories><title-group><article-title>Использование технологий машинного обучения при решении задачи  классификации сигналов мониторинга инфразвукового фона</article-title><trans-title-group xml:lang="en"><trans-title>Using machine learning technologies to solve the problem of classifying infrasound  background monitoring signals</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-9176-6965</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Фролов</surname><given-names>И. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Frolov</surname><given-names>I. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Фролов Иван Николаевич — инженер-программист</p><p>Горно-Алтайск, 649000</p><p> </p></bio><bio xml:lang="en"><p>Ivan N. Frolov — Software Engineer</p><p> Gorno-Altaisk, 649000</p></bio><email xlink:type="simple">xfin@bk.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-1327-5188</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кудрявцев</surname><given-names>Н. Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Kudryavtsev</surname><given-names>N. G.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Кудрявцев Николай Георгиевич — кандидат технических наук, старший научный сотрудник</p><p>Горно-Алтайск, 649000</p><p>sc 57204835030</p></bio><bio xml:lang="en"><p>Nikolai G. Kudryavtsev — PhD, Senior Researcher</p><p> Gorno-Altaisk, 649000</p><p>sc 57204835030</p></bio><email xlink:type="simple">ngkudr@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8043-4014</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сафонова</surname><given-names>В. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Safonova</surname><given-names>V. Yu.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сафонова Варвара Юрьевна — ассистент</p><p>Горно-Алтайск, 649000</p><p>sc 57222578674</p></bio><bio xml:lang="en"><p>Varvara Yu. Safonova — Assistant</p><p> Gorno-Altaisk, 649000</p><p>sc 57222578674</p></bio><email xlink:type="simple">safonova_varvara@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-9174-224X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кудин</surname><given-names>Д. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kudin</surname><given-names>D. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Кудин Дмитрий Владимирович — кандидат технических наук, старший научный сотрудник</p><p>Москва, 119296</p><p>sc 56025952800</p></bio><bio xml:lang="en"><p>Dmitry V. Kudin — PhD, Senior Researcher</p><p>Moscow, 119296</p><p> sc 56025952800</p></bio><email xlink:type="simple">d.kudin@gcras.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Горно-Алтайский государственный университет<country>Россия</country></aff><aff xml:lang="en">Gorno-Altaisk State University (GASU)<country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru">Геофизический центр Российской академии наук<country>Россия</country></aff><aff xml:lang="en">Geophysical Center of The Russian Academy of Sciences (GCRAS)<country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>12</day><month>12</month><year>2024</year></pub-date><volume>24</volume><issue>1</issue><fpage>156</fpage><lpage>164</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Фролов И.Н., Кудрявцев Н.Г., Сафонова В.Ю., Кудин Д.В., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Фролов И.Н., Кудрявцев Н.Г., Сафонова В.Ю., Кудин Д.В.</copyright-holder><copyright-holder xml:lang="en">Frolov I.N., Kudryavtsev N.G., Safonova V.Y., Kudin D.V.</copyright-holder><license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://ntv.elpub.ru/jour/article/view/93">https://ntv.elpub.ru/jour/article/view/93</self-uri><abstract><p>Введение. Широко известно, что среди звуковых сигналов, порождаемых природными и техногенными явлениями, наиболее долгоживущими являются волны частотой менее 20 Гц, именуемые инфразвуком. Это свойство позволяет отслеживать путем инфразвукового мониторинга возникновение высокоэнергетических событий в региональных масштабах на расстоянии до 200–300 км. Вместе с тем выделение полезных инфразвуковых сигналов из фонового шума является нетривиальной задачей при обработке сигналов в реальном времени и постфактум. В работе предлагается новый метод классификации специфических сигналов в данных инфразвукового мониторинга с использованием перестановочной энтропии Шеннона и векторов распределения частот встречаемости перестановок последовательных выборочных значений ранга 3 (количество элементов перестановки). Метод. Для оценки применимости предлагаемого энтропийного метода классификации использованы два метода машинного обучения — метод случайных лесов и классический нейросетевой подход. Методы реализованы на языке Python с использованием библиотек Scikit-lean, TensorFlow и Keras. Выполнена оценка качества классификации по сравнению с традиционным частотным методом выделения классов, основанном на использовании преобразования Фурье. Распознавание проведено на подготовленных данных инфразвукового мониторинга на территории Республики Алтай. Основные результаты. Результаты вычислительного эксперимента по разделению пяти классов сигналов показали, что классификация предложенным методом дает одинаковые результаты распознавания нейронной сетью. При этом по сравнению с частотной классификацией исходных данных точность распознавания составила 51–58 %. Для метода случайных лесов точность распознавания частотных классов равна 51 %, а для метода перестановочной энтропии — 45 %. Обсуждение. Анализ результатов вычислительного эксперимента показал конкурентноспособность метода классификации перестановочной энтропии при распознавании инфразвуковых сигналов. Предлагаемый метод реализуется значительно проще при поточной обработке сигнала в низкопотребляющих микроконтроллерных системах. Планируется дальнейшая апробация метода на пунктах регистрации инфразвуковых сигналов, а также в составе системы обработки данных инфразвукового мониторинга для выделения событий в реальном режиме времени.</p></abstract><trans-abstract xml:lang="en"><p>It is widely known that among sound signals generated by natural and anthropogenic phenomena, the most long-lived are waves of frequency less than 20 Hz, called infrasound. This property allows tracking at a distance by infrasound monitoring the occurrence of high-energy events on regional scales (up to 200–300 km). At the same time, the separation of useful infrasound signals from background noise is a non-trivial task in real-time and post-facto signal processing. In this paper we propose a new method for classification of specific signals in infrasound monitoring data using Shannon permutation entropy and vectors of frequency distribution of occurrence frequencies of permutations of consecutive sample values of rank 3 (number of permutation elements). To evaluate the validity of the proposed entropy-based classification method, two machine learning methods — random forest method and classical neural network approach — implemented in Python language using Scikit-lean, TensorFlow and Keras libraries were used. The classification quality was evaluated against the traditional frequency-based method of class extraction based on Fourier transform. Recognition was performed on the prepared infrasound monitoring data in the Altai Republic. The results of computational experiment on the separation of 5 classes of signals showed that classification by the proposed method gives the same results of recognition by neural network with in comparison with frequency classification of the original data; the recognition accuracy was 51–58 %. For the random forests method, the recognition accuracy of frequency classes was slightly higher: 51 % vs. 45 % for classes using the permutation entropy method. The analysis of the results of the computational experiment shows sufficient competitiveness of the method of classification by permutation entropy in the recognition of infrasound signals. In addition, the proposed method is much easier to implement for inline signal processing in low-consumption microcontroller systems. The next step is to test the method at infrasound signal registration points and as part of the infrasound monitoring data processing system for real-time event detection.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>машинное обучение</kwd><kwd>модель случайного леса</kwd><kwd>искусственная нейронная сеть</kwd><kwd>инфразвук</kwd><kwd>перестановочная  энтропия</kwd><kwd>классификация фрагментов временных рядов</kwd></kwd-group><kwd-group xml:lang="en"><kwd>machine learning</kwd><kwd>random forest model</kwd><kwd>artificial neural network</kwd><kwd>infrasound</kwd><kwd>permutation entropy</kwd><kwd>classification of  time series fragments</kwd></kwd-group><funding-group xml:lang="ru"><funding-statement>Исследование выполнено за счет средств гранта Российского научного фонда и Министерства образования и  науки Республики Алтай № 23-21-10087.</funding-statement></funding-group><funding-group xml:lang="en"><funding-statement>The research was carried out using a grant from the Russian Science Foundation (RSF) and the Ministry of Education  and Science of the Altai Republic No. 23-21-10087</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Sandheep P., Vineeth S., Poulose M., Subha D.P. Performance analysis of deep learning CNN in classification of depression EEG signals // Proc. of the TENCON 2019 — 2019 IEEE Region 10 Conference (TENCON). 2019. P. 1339–1344. https://doi.org/10.1109/TENCON.2019.8929254</mixed-citation><mixed-citation xml:lang="en">Sandheep P., Vineeth S., Poulose M., Subha D.P. Performance analysis of deep learning CNN in classification of depression EEG signals // Proc. of the TENCON 2019 — 2019 IEEE Region 10 Conference (TENCON). 2019. P. 1339–1344. https://doi.org/10.1109/TENCON.2019.8929254</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Heyden M. Classification of EEG data using machine learning techniques: Master’s thesis. Department of Automatic Control, Lund University, 2016.</mixed-citation><mixed-citation xml:lang="en">Heyden M. Classification of EEG data using machine learning techniques: Master’s thesis. Department of Automatic Control, Lund University, 2016.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Guerrero M.C., Parada J.S., Espitia H.E. EEG signal analysis using classification techniques: Logistic regression, artificial neural networks, support vector machines, and convolutional neural networks // Heliyon. 2021. V. 7. N 6. P. e07258. https://doi.org/10.1016/j.heliyon.2021.e07258</mixed-citation><mixed-citation xml:lang="en">Guerrero M.C., Parada J.S., Espitia H.E. EEG signal analysis using classification techniques: Logistic regression, artificial neural networks, support vector machines, and convolutional neural networks // Heliyon. 2021. V. 7. N 6. P. e07258. https://doi.org/10.1016/j.heliyon.2021.e07258</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Siddharth T., Tripathy R., Pachori R. Discrimination of focal and non-focal seizures from EEG signals using sliding mode singular spectrum analysis // IEEE Sensors Journal. 2019. V. 19. N 24. P. 12286–12296. https://doi.org/10.1109/JSEN.2019.2939908</mixed-citation><mixed-citation xml:lang="en">Siddharth T., Tripathy R., Pachori R. Discrimination of focal and non-focal seizures from EEG signals using sliding mode singular spectrum analysis // IEEE Sensors Journal. 2019. V. 19. N 24. P. 12286–12296. https://doi.org/10.1109/JSEN.2019.2939908</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Sharma R., Sircar P., Pachori R.B. A new technique for classification of focal and nonfocal EEG signals using higher-order spectra // Journal of Mechanics in Medicine and Biology. 2019. V. 19. N 1. P. 1940010. https://doi.org/10.1142/S0219519419400104</mixed-citation><mixed-citation xml:lang="en">Sharma R., Sircar P., Pachori R.B. A new technique for classification of focal and nonfocal EEG signals using higher-order spectra // Journal of Mechanics in Medicine and Biology. 2019. V. 19. N 1. P. 1940010. https://doi.org/10.1142/S0219519419400104</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Narayan Y. SEMG signal classification using KNN classifier with FD and TFD features // Materials Today: Proceedings. 2021. V. 37. Part 2. P. 3219–3225. https://doi.org/10.1016/j.matpr.2020.09.089</mixed-citation><mixed-citation xml:lang="en">Narayan Y. SEMG signal classification using KNN classifier with FD and TFD features // Materials Today: Proceedings. 2021. V. 37. Part 2. P. 3219–3225. https://doi.org/10.1016/j.matpr.2020.09.089</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Shi Y., Davaslioglu K., Sagduyu Y.E., Headley W.C., Fowler M., Green G. Deep learning for RF signal classification in unknown and dynamic spectrum environments // Proc. of the 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN). 2019. P. 1–10. https://doi.org/10.1109/DySPAN.2019.8935684</mixed-citation><mixed-citation xml:lang="en">Shi Y., Davaslioglu K., Sagduyu Y.E., Headley W.C., Fowler M., Green G. Deep learning for RF signal classification in unknown and dynamic spectrum environments // Proc. of the 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN). 2019. P. 1–10. https://doi.org/10.1109/DySPAN.2019.8935684</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Shaker A.M., Tantawi M., Shedeed H.A., Tolba M.F. Generalization of convolutional neural networks for ECG classification using generative adversarial networks // IEEE Access. 2020. V. 8. P. 35592– 35605. https://doi.org/10.1109/ACCESS.2020.2974712</mixed-citation><mixed-citation xml:lang="en">Shaker A.M., Tantawi M., Shedeed H.A., Tolba M.F. Generalization of convolutional neural networks for ECG classification using generative adversarial networks // IEEE Access. 2020. V. 8. P. 35592– 35605. https://doi.org/10.1109/ACCESS.2020.2974712</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Donmez H., Ozkurt N. Emotion classification from EEG signals in convolutional neural networks // Proc. of the 2019 Innovations in Intelligent Systems and Applications Conference (ASYU). 2019. P. 1–6. https://doi.org/10.1109/ASYU48272.2019.8946364</mixed-citation><mixed-citation xml:lang="en">Donmez H., Ozkurt N. Emotion classification from EEG signals in convolutional neural networks // Proc. of the 2019 Innovations in Intelligent Systems and Applications Conference (ASYU). 2019. P. 1–6. https://doi.org/10.1109/ASYU48272.2019.8946364</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Кузин Д.А., Стаценко Л.Г., Анисимов П.Н., Смирнова М.М. Применение методов машинного обучения для классификации акустических сигналов по спектральным характеристикам // Известия СПбГЭТУ ЛЭТИ. 2021. № 3. С. 48–54.</mixed-citation><mixed-citation xml:lang="en">Kuzin D.A., Statsenko L.G., Anisimov P.N., Smirnova M.M. Applying machine learning methods to acoustic signal classification using spectrum characteristics. Proceedings of Saint Petersburg Electrotechnical University, 2021, no. 3, pp. 48–54. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Wu Y., Zhang J., Chen X., Zou S., Yang M. Research on the recognition of infrasound signal of nuclear explosion by SVM and CNN // IOP Conference Series: Earth and Environmental Science. 2020. V. 610. P. 012010. https://doi.org/10.1088/1755-1315/610/1/012010</mixed-citation><mixed-citation xml:lang="en">Wu Y., Zhang J., Chen X., Zou S., Yang M. Research on the recognition of infrasound signal of nuclear explosion by SVM and CNN // IOP Conference Series: Earth and Environmental Science. 2020. V. 610. P. 012010. https://doi.org/10.1088/1755-1315/610/1/012010</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Traversaro F., Redelico F.O., Risk M.R., Frery A.C., Rosso O.A. Bandt-Pompe symbolization dynamics for time series with tied values: A data-driven approach // Chaos. 2018. V. 28. N 7. P. 075502. https://doi.org/10.1063/1.5022021</mixed-citation><mixed-citation xml:lang="en">Traversaro F., Redelico F.O., Risk M.R., Frery A.C., Rosso O.A. Bandt-Pompe symbolization dynamics for time series with tied values: A data-driven approach // Chaos. 2018. V. 28. N 7. P. 075502. https://doi.org/10.1063/1.5022021</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Константинов А.В., Лештаев В.С. Подготовка признакового пространства нейросетевой модели для классификации сейсмо-акустических событий системы PROGNOZ-ADS // 5-я конференция Международной научной школы академика РАН К.Н. Трубецкого «Проблемы и перспективы комплексного освоения и сохранения земных недр», 14–18 ноября 2022, Москва. М.: ИПКОН РАН, 2022. C. 108–112.</mixed-citation><mixed-citation xml:lang="en">Konstantinov A.V., Leshtaev V.S. Preparing the feature space of a neural network model for the classification of seismoacoustic events of the PROGNOZ-ADS system. Proc. of the 5th conference of the International Scientific School of Academician K.N. Trubetskoy from the Russian Academy of Sciences “Problems and prospects for the integrated development and conservation of the earth interior”. Moscow, IPKON RAS, 2022, pp. 108–112. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Jiao S., Geng B., Li Y., Zhang Q., Wang Q. Fluctuation-based reverse dispersion entropy and its applications to signal classification // Applied Acoustics. 2021. V. 175. P. 107857. https://doi.org/10.1016/j.apacoust.2020.107857</mixed-citation><mixed-citation xml:lang="en">Jiao S., Geng B., Li Y., Zhang Q., Wang Q. Fluctuation-based reverse dispersion entropy and its applications to signal classification // Applied Acoustics. 2021. V. 175. P. 107857. https://doi.org/10.1016/j.apacoust.2020.107857</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Кузнецов И.А. Методы и алгоритмы машинного обучения для предобработки и классификации слабоструктурированных текстовых данных в научных рекомендательных системах: диссертация на соискание ученой степени кандидата технических наук. М.: МИФИ, 2019. 127 c.</mixed-citation><mixed-citation xml:lang="en">Kuznetcov I.A. Machine learning methods and algorithms for preprocessing and classification of semi-structured text data in scientific recommendation systems. Dissertation for the degree of candidate of technical sciences. Moscow, MEPhI, 2019, 127 p. (in Russian)</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
