<?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">zhps</journal-id><journal-title-group><journal-title xml:lang="ru">Журнал прикладной спектроскопии</journal-title><trans-title-group xml:lang="en"><trans-title>Zhurnal Prikladnoii Spektroskopii</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">0514-7506</issn><publisher><publisher-name>B. I. Stepanov Institute of Physics of the National Academy of Sciences</publisher-name></publisher></journal-meta><article-meta><article-id custom-type="elpub" pub-id-type="custom">zhps-1778</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>АННОТАЦИИ АНГЛОЯЗЫЧНЫХ СТАТЕЙ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>ABSTRACTS ENGLISH-LANGUAGE ARTICLES</subject></subj-group></article-categories><title-group><article-title>Метод извлечения переменных признаков на основе сверточной нейронной сети при обработке данных лазерно-искровой эмиссионной спектроскопии</article-title><trans-title-group xml:lang="en"><trans-title>LIBS FEATURE VARIABLE EXTRACTION METHOD BASED ON CONVOLUTIONAL NEURAL NETWORK</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Lin</surname><given-names>X.</given-names></name><name name-style="western" xml:lang="en"><surname>Lin</surname><given-names>X.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Цюаньчжоу, Фуцзянь</p></bio><bio xml:lang="en"><p>Quanzhou, Fujian</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Gao</surname><given-names>S.</given-names></name><name name-style="western" xml:lang="en"><surname>Gao</surname><given-names>S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Цюаньчжоу, Фуцзянь</p></bio><bio xml:lang="en"><p>Quanzhou, Fujian</p></bio><email xlink:type="simple">187049860@qq.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Du</surname><given-names>Y.</given-names></name><name name-style="western" xml:lang="en"><surname>Du</surname><given-names>Y.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Цюаньчжоу, Фуцзянь</p></bio><bio xml:lang="en"><p>Quanzhou, Fujian</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Yang</surname><given-names>Y.</given-names></name><name name-style="western" xml:lang="en"><surname>Yang</surname><given-names>Y.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Чанчунь, Цзилинь</p></bio><bio xml:lang="en"><p>Changchun, Jilin</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Che</surname><given-names>C.</given-names></name><name name-style="western" xml:lang="en"><surname>Che</surname><given-names>C.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Цзилинь</p></bio><bio xml:lang="en"><p>Jilin</p></bio><xref ref-type="aff" rid="aff-3"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Университет информационной инженерии Цюаньчжоу</institution></aff><aff xml:lang="en"><institution>Quanzhou University of Information Engineering</institution></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Qiming Information Technology Co., Ltd.</institution></aff><aff xml:lang="en"><institution>Qiming Information Technology Co., Ltd.</institution></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>Университет Бэйхуа</institution></aff><aff xml:lang="en"><institution>Beihua University</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>07</day><month>02</month><year>2025</year></pub-date><volume>92</volume><issue>1</issue><fpage>139</fpage><lpage>139</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Lin X., Gao S., Du Y., Yang Y., Che C., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Lin X., Gao S., Du Y., Yang Y., Che C.</copyright-holder><copyright-holder xml:lang="en">Lin X., Gao S., Du Y., Yang Y., Che C.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" 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://zhps.ejournal.by/jour/article/view/1778">https://zhps.ejournal.by/jour/article/view/1778</self-uri><abstract><p>Извлечение переменных признаков может значительно уменьшить размерность, упростить признаки и повысить точность количественных моделей, что имеет большое значение при предварительной обработке спектральных данных лазерно-искровой эмиссионной спектроскопии (LIBS). Предложен метод извлечения переменных признаков на основе сверточной нейронной сети (CNN). Спектральные данные LIBS подвергались многослойной двумерной свертке путем последовательного соединения структуры свертки и модуля InceptionV2, многоуровневые признаки постепенно извлекались для нахождения оптимальной комбинации переменных признаков. С помощью полносвязного слоя получены результаты прогнозирования. С целью проверки применимости извлеченных признаков результаты, выделенные сверточной нейронной сетью, напрямую вводились в алгоритм случайного леса (RF) для построения количественной модели. Определена концентрация элемента K в лабораторном смешанном растворе. При обработке методом CNN-RF коэффициенты детерминации R2 обучающей и тестовой выборок составили 0.993 и 0.990, среднеквадратическая ошибка обучающей и тестовой выборок RMSEC = 0.0067 и RMSEP = 0.0084 мас.%, средняя относительная ошибка 8.533%. Полученные оценки значительно лучше, чем результаты извлечения с помощью методов Lasso, РСА и SelectKBest. Показано, что сверточная нейронная сеть позволяет эффективно извлекать характерные спектральные линии LIBS и повышать точность количественного анализа. </p></abstract><trans-abstract xml:lang="en"><p>The extraction of feature variables can significantly reduce the dimension, simplify the features, and improve the accuracy of quantitative models, which is of great significance in spectral data preprocessing using laser-induced breakdown spectroscopy (LIBS). A feature variable extraction method based on convolutional neural network was proposed. The LIBS spectral data was subjected to multilayer two-dimensional convolution through the series connection of the convolution structure and an InceptionV2 module, and the multi-level features were gradually extracted to find the optimal feature variable combination. Finally, the prediction results were obtained by the fully connected layer. In order to verify the applicability of the extracted features, the extraction results of the convolutional neural network were directly input into random forest to construct a quantitative model. In this paper, the concentration of K element in the mixed solution prepared by the laboratory was tested. The determination coefficients R2  of the CNN-RF training set and the test set reached 0.993 and 0.990, respectively. The root mean square error (RMSEC) of the training set and the root mean square error (RMSEP) of the test set were 0.0067 and 0.0084 wt.%, respectively, and the average relative error reached 8.533%. The evaluation parameters were significantly better than the extraction results of least absolute shrinkage and selection operator, principal component analysis and SelectKBest. The results show that the convolutional neural network can effectively extract LIBS characteristic spectral lines and improve the accuracy of quantitative analysis.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>лазерно-искровая эмиссионная спектроскопия</kwd><kwd>извлечение переменных признаков</kwd><kwd>сверточная нейронная сеть</kwd></kwd-group><kwd-group xml:lang="en"><kwd>laser-induced breakdown spectroscopy</kwd><kwd>feature variable extraction</kwd><kwd>convolutional neural network</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">F. Deng, Y. Ding, Y. Chen, et al., J. Plasma Sci. Technol., 22, No. 7, 074005(1–8) (2020), doi: 10.1088/2058-6272/ab77d5.</mixed-citation><mixed-citation xml:lang="en">F. Deng, Y. Ding, Y. Chen, et al., J. Plasma Sci. Technol., 22, No. 7, 074005(1–8) (2020), doi: 10.1088/2058-6272/ab77d5.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Z. Wanwan, J. Mingzhe, J. Comp., 7, No. 7 (2022), doi: 10.1093/comjnl/bxac033.</mixed-citation><mixed-citation xml:lang="en">Z. Wanwan, J. Mingzhe, J. Comp., 7, No. 7 (2022), doi: 10.1093/comjnl/bxac033.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Tomas Lopes et al., Appl. Spectrosc., 7028241246545 (2024).</mixed-citation><mixed-citation xml:lang="en">Tomas Lopes et al., Appl. Spectrosc., 7028241246545 (2024).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">A. Kumar, P. S. V. S. S. Prasad, Int. J. Approx. Reasoning, 139, 69–87 (2021), doi: 10.1016/j.ijar.2021.09.006.</mixed-citation><mixed-citation xml:lang="en">A. Kumar, P. S. V. S. S. Prasad, Int. J. Approx. Reasoning, 139, 69–87 (2021), doi: 10.1016/j.ijar.2021.09.006.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">C. Yan, J. Liang, M. Zhao, et al., J. Analyt. Chim. Acta, 1080, 35–42 (2019), doi: 10.1016/j.aca.2019.07.012.</mixed-citation><mixed-citation xml:lang="en">C. Yan, J. Liang, M. Zhao, et al., J. Analyt. Chim. Acta, 1080, 35–42 (2019), doi: 10.1016/j.aca.2019.07.012.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">G. X. X. Cui, J. Plasma Sci. Technol., 23, No. 5 (2021).</mixed-citation><mixed-citation xml:lang="en">G. X. X. Cui, J. Plasma Sci. Technol., 23, No. 5 (2021).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">W. Zhao, et al., Analyt. Chim. Acta, 1166, 338574 (2021).</mixed-citation><mixed-citation xml:lang="en">W. Zhao, et al., Analyt. Chim. Acta, 1166, 338574 (2021).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">F. Deng, Y. Ding, Y. Chen, et al., J. Plasma Sci. Technol., 22, No. 7, 074005(1–8) (2020), doi: 10.1088/2058-6272/ab77d5.</mixed-citation><mixed-citation xml:lang="en">F. Deng, Y. Ding, Y. Chen, et al., J. Plasma Sci. Technol., 22, No. 7, 074005(1–8) (2020), doi: 10.1088/2058-6272/ab77d5.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">A. Erler, D. Riebe, T. Beitz, et al., Sensors, 20, No. 2, 418 (2020), doi: 10.3390/s20020418.</mixed-citation><mixed-citation xml:lang="en">A. Erler, D. Riebe, T. Beitz, et al., Sensors, 20, No. 2, 418 (2020), doi: 10.3390/s20020418.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Y. Zhang, C. Sun, Z. Yue, et al., J. Opt. Express, 28, No. 21, 32019 (2020), doi: 10.1364/OE.404722.</mixed-citation><mixed-citation xml:lang="en">Y. Zhang, C. Sun, Z. Yue, et al., J. Opt. Express, 28, No. 21, 32019 (2020), doi: 10.1364/OE.404722.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Wu Yiqing, Sun Tong, Liu Jin, et al., J. Laser Optoelectron. Progress, 55, No. 1, 013005 (2018), doi: 10.3788/LOP55.013005.</mixed-citation><mixed-citation xml:lang="en">Wu Yiqing, Sun Tong, Liu Jin, et al., J. Laser Optoelectron. Progress, 55, No. 1, 013005 (2018), doi: 10.3788/LOP55.013005.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Deng Zhang et al., Microchem. J. (2024).</mixed-citation><mixed-citation xml:lang="en">Deng Zhang et al., Microchem. J. (2024).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">C. Sun, Y. Tian, L. Gao, et al., J. Sci. Rep., 9, No. 1, 11363 (2019), doi: 10.1038/s41598-019-47751-y.</mixed-citation><mixed-citation xml:lang="en">C. Sun, Y. Tian, L. Gao, et al., J. Sci. Rep., 9, No. 1, 11363 (2019), doi: 10.1038/s41598-019-47751-y.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Z. Fei-Yan, J. Lin-Peng, D. Jun, Chin. J. Comp. (2017), doi: 10.11897/SP.J.1016.2017.01229.</mixed-citation><mixed-citation xml:lang="en">Z. Fei-Yan, J. Lin-Peng, D. Jun, Chin. J. Comp. (2017), doi: 10.11897/SP.J.1016.2017.01229.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">C. A. O. Xue, et al., Plasma Sci. Technol., 22, No. 11, 115502 (2020).</mixed-citation><mixed-citation xml:lang="en">C. A. O. Xue, et al., Plasma Sci. Technol., 22, No. 11, 115502 (2020).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Y. Gou, X. Fu, S. Zhao, et al., J. Spectrochim. Acta, B: At. Spectrosc., 215 (2024), doi: 10.1016/j.sab.2024.106910.</mixed-citation><mixed-citation xml:lang="en">Y. Gou, X. Fu, S. Zhao, et al., J. Spectrochim. Acta, B: At. Spectrosc., 215 (2024), doi: 10.1016/j.sab.2024.106910.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Yanhong Gu, et al., Electronics, 12, No. 12, 2566 (2023).</mixed-citation><mixed-citation xml:lang="en">Yanhong Gu, et al., Electronics, 12, No. 12, 2566 (2023).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">L. I. Yandong, H. Zongbo, L. Hang, J. Comp. Applications, 36(009), 2508–2515 (2016).</mixed-citation><mixed-citation xml:lang="en">L. I. Yandong, H. Zongbo, L. Hang, J. Comp. Applications, 36(009), 2508–2515 (2016).</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">K. Dhiwar, A. K. Dewangan, Int. J. Scientific Research in Science, Engineering and Technology, 2, No. 2, 1167–1171 (2016).</mixed-citation><mixed-citation xml:lang="en">K. Dhiwar, A. K. Dewangan, Int. J. Scientific Research in Science, Engineering and Technology, 2, No. 2, 1167–1171 (2016).</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">F. Sultana, A. Sufian, P. Dutta, A Review of Object Detection Models based on Convolutional Neural Network, in “Intelligent Computing: Image Processing Based Applications”, 1–16 (2020), doi: 10.1007/978-981-15-4288-61.</mixed-citation><mixed-citation xml:lang="en">F. Sultana, A. Sufian, P. Dutta, A Review of Object Detection Models based on Convolutional Neural Network, in “Intelligent Computing: Image Processing Based Applications”, 1–16 (2020), doi: 10.1007/978-981-15-4288-61.</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>
