<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.2 20190208//EN"
  "https://jats.nlm.nih.gov/publishing/1.2/JATS-journalpublishing1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink"
         xmlns:mml="http://www.w3.org/1998/Math/MathML"
         article-type="research-article"
         xml:lang="ru"
         dtd-version="1.2">

  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">tis</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">Телекоммуникации и связь</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>Telecommunications and Communications</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">3034-4050</issn>
      <publisher>
        <publisher-name>ФГБУ «16 ЦНИИИ»</publisher-name>
      </publisher>
    </journal-meta>

    <article-meta>
      <article-id pub-id-type="doi">10.21681/3034-4050-2025-6-20-27</article-id>

      <article-categories>
        <subj-group subj-group-type="udc">
          <compound-subject>
            <compound-subject-part content-type="udc">004.8</compound-subject-part>
          </compound-subject>
        </subj-group>
      </article-categories>

      <title-group>
        <article-title xml:lang="ru">ИССЛЕДОВАНИЕ ПРИМЕНИМОСТИ НЕЙРОННЫХ СЕТЕЙ В ЗАДАЧАХ АНАЛИЗА ГИДРОАКУСТИЧЕСКИХ СИГНАЛОВ ДЛЯ ПОВЫШЕНИЯ ЭФФЕКТИВНОСТИ ОБНАРУЖЕНИЯ ПОДВОДНЫХ ЦЕЛЕЙ</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>STUDY OF THE APPLICABILITY OF NEURAL NETWORKS IN THE ANALYSIS OF HYDROACOUSTIC SIGNALS TO IMPROVE THE EFFICIENCY OF DETECTING UNDERWATER TARGETS</trans-title>
        </trans-title-group>
      </title-group>

      <contrib-group>
        <contrib contrib-type="author">
          <name>
            <surname>Григоренко</surname>
            <given-names>Александр Сергеевич</given-names>
          </name>
          <name-alternatives>
            <name xml:lang="en">
              <surname>Grigorenko</surname>
              <given-names>Alexander S.</given-names>
            </name>
          </name-alternatives>
          <aff id="aff1">
            <institution>младший научный сотрудник, Военная академия связи</institution>
            <city>Санкт-Петербург</city>
            <country>Россия</country>
          </aff>
          <email>grigorenko.201@mail.ru</email>
        </contrib>
        <contrib contrib-type="author">
          <name>
            <surname>Ситдиков</surname>
            <given-names>Дмитрий Сергеевич</given-names>
          </name>
          <name-alternatives>
            <name xml:lang="en">
              <surname>Sitdikov</surname>
              <given-names>Dmitry G.</given-names>
            </name>
          </name-alternatives>
          <aff id="aff2">
            <institution>младший научный сотрудник, Военная академия связи</institution>
            <city>Санкт-Петербург</city>
            <country>Россия</country>
          </aff>
          <email>dima.sitdikov.99@mail.ru</email>
        </contrib>
      </contrib-group>

      <pub-date pub-type="epub">
        <year>2025</year>
      </pub-date>
      <pub-date pub-type="collection">
        <year>2025</year>
      </pub-date>

      <volume>11</volume>
      <issue>2</issue>
      <fpage>20</fpage>
      <lpage>27</lpage>

      <permissions>
        <copyright-year>2025</copyright-year>
      </permissions>

      <self-uri xlink:href="https://telemil.ru/pages/archive/magazine9/%D0%A2%D0%B8%D0%A1_6_2025-20-27.pdf">https://telemil.ru/pages/archive/magazine9/ТиС_6_2025-20-27.pdf</self-uri>
      <self-uri xlink:href="ТиС_6_2025-20-27.xml" content-type="jats">JATS XML</self-uri>

      <abstract xml:lang="ru">
        <title>Аннотация</title>
        <p>&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;Целью работы&lt;/b&gt; является анализ применимости методов глубокого обучения к автоматизированной обработке и классификации гидроакустических сигналов для повышения эффективности обнаружения подводных целей, а также экспериментальная проверка одного из подходов на открытом наборе данных DeepShip с использованием архитектуры ResNet-50.&lt;/p&gt;&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;Метод исследования:&lt;/b&gt; применение систематического обзора публикаций 2020–2025 гг., охватывающий свёрточные, рекуррентные, трансформерные модели и денойзинг-автоэнкодеры и проведении эксперимента, который включает преобразование аудиозаписей в трёхканальные спектрограммы (две низкочастотные полосы и одна высокочастотная), лог-нормализацию и масштабирование в [0,1], случайное разбиение выборки (80/20) с сохранением пропорций классов, тонкую настройку предобученной ResNet-50 при функции потерь бинарной кросс-энтропии, оптимизаторе Adam, ранней остановке и выборе лучшей модели по точности.&lt;/p&gt;&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;Результаты исследования:&lt;/b&gt; обобщены современные подходы к анализу гидроакустических данных: свёрточные сети над спектрограммами надёжно извлекают локальные признаки и обеспечивают высокую точность классификации; рекуррентные (LSTM/GRU) улучшают учёт временной динамики и трекинг целей; трансформеры с механизмом самовнимания повышают качество при длинных зависимостях и эффективны для детекции на сонарных изображениях; денойзинг-автоэнкодеры снижают влияние нестационарных помех и повышают отношение сигнал/шум. В проведённом эксперименте ResNet-50 на трёхканальных LF/HF-спектрограммах достигла 95 % точности на валидации и 93 % тесте, что подтверждает практическую применимость подхода. Отмечены ограничения реальной эксплуатации: вариативность шумовой среды, дефицит размеченных данных и риски недостаточной интерпретируемости решений; предложены направления совершенствования – расширенные аугментации, перенос обучения.&lt;/p&gt;&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;Научная новизна&lt;/b&gt; заключается в экспериментально подтверждённой схеме трёхканального спектрального представления для ResNet-50, задающей практические требования к точности и дальнейшей интеграции в системы подводного наблюдения.&lt;/p&gt;</p>
      </abstract>

      <trans-abstract xml:lang="en">
        <title>Abstract</title>
        <p>&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;Purpose of the work&lt;/b&gt; is to analyze the applicability of deep learning methods to automated processing and classification of hydroacoustic signals to improve the efficiency of detecting underwater targets, as well as to experimentally test one of the approaches on an open DeepShip dataset using the ResNet-50 architecture.&lt;/p&gt;&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;Research method:&lt;/b&gt; application of a systematic review of publications in 2020–2025, covering convolution, recurrent, transformer models and denoised autoencoders, and conducting an experiment that includes the transformation of audio recordings into three-channel spectrograms (two low-frequency bands and one high-frequency), log-normalization and scaling to [0,1], random sample splitting (80/20) while maintaining class proportions, fine-tuning of the pre-trained ResNet-50 at the binary cross-entropy loss, Adam optimizer, early stop and selection of the best model for accuracy.&lt;/p&gt;&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;Results of the study:&lt;/b&gt; modern approaches to the analysis of hydroacoustic data are summarized: convolutional networks over spectrograms reliably extract local features and provide high classification accuracy; recurrent networks (LSTM/GRU) improve time dynamics accounting and target tracking; transformers with a self-attention mechanism improve quality with long dependencies and are effective for detection on sonar images; denoising autoencoders reduce the influence of non-stationary interference and increase the signal-to-noise ratio. In the ResNet-50 experiment on three-channel LF/HF spectrograms, it achieved 95 % accuracy in validation and 93 % in the test, which confirms the practical applicability of the approach. The limitations of real operation are noted: variability of the noise environment, lack of labeled data and risks of insufficient interpretability of decisions; Directions for improvement are proposed, such as extended augmentations, transfer of training.&lt;/p&gt;&lt;p class=&quot;section-text&quot;&gt;&lt;b&gt;The scientific novelty&lt;/b&gt; lies in the experimentally confirmed scheme of three-channel spectral representation for ResNet-50, which sets practical requirements for accuracy and further integration into underwater surveillance systems.&lt;/p&gt;</p>
      </trans-abstract>

      <kwd-group xml:lang="ru">
        <title>Ключевые слова</title>
        <kwd>сверточные сети</kwd>
        <kwd>рекуррентные сети</kwd>
        <kwd>трансформеры</kwd>
        <kwd>автоэнкодеры</kwd>
        <kwd>спектрограммы</kwd>
        <kwd>классификация судов</kwd>
      </kwd-group>

      <kwd-group xml:lang="en">
        <title>Keywords</title>
        <kwd>convolutional networks</kwd>
        <kwd>recurrent networks</kwd>
        <kwd>transformers</kwd>
        <kwd>autoencoders</kwd>
        <kwd>spectrograms</kwd>
        <kwd>ship classification</kwd>
      </kwd-group>

      <funding-group>
        <funding-statement>Источники финансирования не указаны.</funding-statement>
      </funding-group>

    </article-meta>
  </front>

  <back>
    <ref-list>
      <title>Список литературы / References</title>
      <ref id="ref1">
        <label>1</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Lin X., Dong R., Lv Z.</string-name>
          </person-group>
          <article-title xml:lang="ru">Deep learning-based classification of raw hydroacoustic signal: A review</article-title>
          <trans-title-group xml:lang="en"><trans-title>Deep learning-based classification of raw hydroacoustic signal: A review</trans-title></trans-title-group>
          <source xml:lang="ru">Journal of Marine Science and Engineering</source>
          <trans-source xml:lang="en">Journal of Marine Science and Engineering</trans-source>
          <year>2022</year>
          <volume>11</volume>
          <issue>1</issue>
          <fpage>3</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref2">
        <label>2</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Lin X. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">Efficient ship noise classification with positive incentive noise and fused features using a simple convolutional network</article-title>
          <trans-title-group xml:lang="en"><trans-title>Efficient ship noise classification with positive incentive noise and fused features using a simple convolutional network</trans-title></trans-title-group>
          <source xml:lang="ru">Scientific Reports</source>
          <trans-source xml:lang="en">Scientific Reports</trans-source>
          <year>2023</year>
          <volume>13</volume>
          <issue>1</issue>
          <fpage>17905</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref3">
        <label>3</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Guo T. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">Underwater target detection and localization with feature map and CNN-based classification</article-title>
          <trans-title-group xml:lang="en"><trans-title>Underwater target detection and localization with feature map and CNN-based classification</trans-title></trans-title-group>
          <source xml:lang="ru">2022 4th International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)</source>
          <trans-source xml:lang="en">2022 4th International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)</trans-source>
          <year>2022</year>
          
          
          <fpage>1</fpage>
          <lpage>8</lpage>
          
        </element-citation>
      </ref>
      <ref id="ref4">
        <label>4</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Liu Y., Chen H., Wang B.</string-name>
          </person-group>
          <article-title xml:lang="ru">DOA estimation based on CNN for underwater acoustic array</article-title>
          <trans-title-group xml:lang="en"><trans-title>DOA estimation based on CNN for underwater acoustic array</trans-title></trans-title-group>
          <source xml:lang="ru">Applied Acoustics</source>
          <trans-source xml:lang="en">Applied Acoustics</trans-source>
          <year>2021</year>
          <volume>172</volume>
          
          <fpage>107594</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref5">
        <label>5</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Abayomi-Alli O. O. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">Data augmentation and deep learning methods in sound classification: A systematic review</article-title>
          <trans-title-group xml:lang="en"><trans-title>Data augmentation and deep learning methods in sound classification: A systematic review</trans-title></trans-title-group>
          <source xml:lang="ru">Electronics</source>
          <trans-source xml:lang="en">Electronics</trans-source>
          <year>2022</year>
          <volume>11</volume>
          <issue>22</issue>
          <fpage>3795</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref6">
        <label>6</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Mishachandar B., Vairamuthu S.</string-name>
          </person-group>
          <article-title xml:lang="ru">Diverse ocean noise classification using deep learning</article-title>
          <trans-title-group xml:lang="en"><trans-title>Diverse ocean noise classification using deep learning</trans-title></trans-title-group>
          <source xml:lang="ru">Applied Acoustics</source>
          <trans-source xml:lang="en">Applied Acoustics</trans-source>
          <year>2021</year>
          <volume>181</volume>
          
          <fpage>108141</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref7">
        <label>7</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Wang Y. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">Passive sonar target tracking based on deep learning</article-title>
          <trans-title-group xml:lang="en"><trans-title>Passive sonar target tracking based on deep learning</trans-title></trans-title-group>
          <source xml:lang="ru">Journal of Marine Science and Engineering</source>
          <trans-source xml:lang="en">Journal of Marine Science and Engineering</trans-source>
          <year>2022</year>
          <volume>10</volume>
          <issue>2</issue>
          <fpage>181</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref8">
        <label>8</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Li P. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">STM: Spectrogram transformer model for underwater acoustic target recognition</article-title>
          <trans-title-group xml:lang="en"><trans-title>STM: Spectrogram transformer model for underwater acoustic target recognition</trans-title></trans-title-group>
          <source xml:lang="ru">Journal of Marine Science and Engineering</source>
          <trans-source xml:lang="en">Journal of Marine Science and Engineering</trans-source>
          <year>2022</year>
          <volume>10</volume>
          <issue>10</issue>
          <fpage>1428</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref9">
        <label>9</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Wen X. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">Underwater side-scan sonar target detection: YOLOv7 model combined with attention mechanism and scaling factor</article-title>
          <trans-title-group xml:lang="en"><trans-title>Underwater side-scan sonar target detection: YOLOv7 model combined with attention mechanism and scaling factor</trans-title></trans-title-group>
          <source xml:lang="ru">Remote Sensing</source>
          <trans-source xml:lang="en">Remote Sensing</trans-source>
          <year>2024</year>
          <volume>16</volume>
          <issue>13</issue>
          <fpage>2492</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref10">
        <label>10</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Song Y. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">Underwater acoustic signal noise reduction based on a fully convolutional encoder-decoder neural network</article-title>
          <trans-title-group xml:lang="en"><trans-title>Underwater acoustic signal noise reduction based on a fully convolutional encoder-decoder neural network</trans-title></trans-title-group>
          <source xml:lang="ru">Journal of Ocean University of China</source>
          <trans-source xml:lang="en">Journal of Ocean University of China</trans-source>
          <year>2023</year>
          <volume>22</volume>
          <issue>6</issue>
          <fpage>1487</fpage>
          <lpage>1496</lpage>
          
        </element-citation>
      </ref>
      <ref id="ref11">
        <label>11</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Panteli E., Santos P. E., Humphrey N.</string-name>
          </person-group>
          <article-title xml:lang="ru">AquaSignal: An Integrated Framework for Robust Underwater Acoustic Analysis</article-title>
          <trans-title-group xml:lang="en"><trans-title>AquaSignal: An Integrated Framework for Robust Underwater Acoustic Analysis</trans-title></trans-title-group>
          <source xml:lang="ru">arXiv preprint arXiv:2505.14285</source>
          <trans-source xml:lang="en">arXiv preprint arXiv:2505.14285</trans-source>
          <year>2025</year>
          
          
          
          
          
        </element-citation>
      </ref>
      <ref id="ref12">
        <label>12</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Hummel H. I., van der Mei R., Bhulai S.</string-name>
          </person-group>
          <article-title xml:lang="ru">A survey on machine learning in ship radiated noise</article-title>
          <trans-title-group xml:lang="en"><trans-title>A survey on machine learning in ship radiated noise</trans-title></trans-title-group>
          <source xml:lang="ru">Ocean Engineering</source>
          <trans-source xml:lang="en">Ocean Engineering</trans-source>
          <year>2024</year>
          <volume>298</volume>
          
          <fpage>117252</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref13">
        <label>13</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Akman A., Schuller B. W.</string-name>
          </person-group>
          <article-title xml:lang="ru">Audio explainable artificial intelligence: A review</article-title>
          <trans-title-group xml:lang="en"><trans-title>Audio explainable artificial intelligence: A review</trans-title></trans-title-group>
          <source xml:lang="ru">Intelligent Computing</source>
          <trans-source xml:lang="en">Intelligent Computing</trans-source>
          <year>2024</year>
          <volume>2</volume>
          
          <fpage>0074</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref14">
        <label>14</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Cheng Z. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">A Comprehensive Review of Explainable Artificial Intelligence (XAI) in Computer Vision</article-title>
          <trans-title-group xml:lang="en"><trans-title>A Comprehensive Review of Explainable Artificial Intelligence (XAI) in Computer Vision</trans-title></trans-title-group>
          <source xml:lang="ru">Sensors</source>
          <trans-source xml:lang="en">Sensors</trans-source>
          <year>2025</year>
          <volume>25</volume>
          <issue>13</issue>
          <fpage>4166</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref15">
        <label>15</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Tian S. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">Deep convolution stack for waveform in underwater acoustic target recognition</article-title>
          <trans-title-group xml:lang="en"><trans-title>Deep convolution stack for waveform in underwater acoustic target recognition</trans-title></trans-title-group>
          <source xml:lang="ru">Scientific reports</source>
          <trans-source xml:lang="en">Scientific reports</trans-source>
          <year>2021</year>
          <volume>11</volume>
          <issue>1</issue>
          <fpage>9614</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref16">
        <label>16</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Zhang Z. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">ESL-YOLO: Edge-Aware Side-Scan Sonar Object Detection with Adaptive Quality Assessment</article-title>
          <trans-title-group xml:lang="en"><trans-title>ESL-YOLO: Edge-Aware Side-Scan Sonar Object Detection with Adaptive Quality Assessment</trans-title></trans-title-group>
          <source xml:lang="ru">Journal of Marine Science and Engineering</source>
          <trans-source xml:lang="en">Journal of Marine Science and Engineering</trans-source>
          <year>2025</year>
          <volume>13</volume>
          <issue>8</issue>
          <fpage>1477</fpage>
          
          
        </element-citation>
      </ref>
      <ref id="ref17">
        <label>17</label>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <string-name>Tang Y. et al.</string-name>
          </person-group>
          <article-title xml:lang="ru">AUV-based side-scan sonar real-time method for underwater-target detection</article-title>
          <trans-title-group xml:lang="en"><trans-title>AUV-based side-scan sonar real-time method for underwater-target detection</trans-title></trans-title-group>
          <source xml:lang="ru">Journal of Marine Science and Engineering</source>
          <trans-source xml:lang="en">Journal of Marine Science and Engineering</trans-source>
          <year>2023</year>
          <volume>11</volume>
          <issue>4</issue>
          <fpage>690</fpage>
          
          
        </element-citation>
      </ref>
    </ref-list>
  </back>

</article>