<?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">10.17586/2226-1494-2024-24-3-474-482</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-355</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>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Метод формирования сегментов информационной последовательности с использованием функционала качества моделей обработки</article-title><trans-title-group xml:lang="en"><trans-title>Method for generating information sequence segments using the quality functional of processing models</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0008-0128-4144</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тихонов</surname><given-names>Д. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Tikhonov</surname><given-names>D. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Тихонов Даниил Дмитриевич — аспирант, инженер-программист</p><p>Санкт-Петербург, 199178</p></bio><bio xml:lang="en"><p>Daniil D. Tikhonov — PhD Student, Programmer</p><p>Saint Petersburg, 199178</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-6753-2181</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Лебедев</surname><given-names>И. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Lebedev</surname><given-names>I. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Лебедев Илья Сергеевич — доктор технических наук, профессор, заведующий лабораторией</p><p>Санкт-Петербург, 199178</p></bio><bio xml:lang="en"><p>Ilya S. Lebedev — D.Sc., Professor, Head of Laboratory</p><p>Saint Petersburg, 199178</p></bio><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский Федеральный исследовательский центр Российской академии наук</institution><country>Россия</country></aff><aff xml:lang="en"><institution>St. Petersburg Federal Research Center of the Russian Academy of Sciences</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>19</day><month>12</month><year>2024</year></pub-date><volume>24</volume><issue>3</issue><fpage>474</fpage><lpage>482</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Тихонов Д.Д., Лебедев И.С., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Тихонов Д.Д., Лебедев И.С.</copyright-holder><copyright-holder xml:lang="en">Tikhonov D.D., Lebedev I.S.</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://ntv.elpub.ru/jour/article/view/355">https://ntv.elpub.ru/jour/article/view/355</self-uri><abstract><sec><title>Введение</title><p>Введение. Постоянно возникающая потребность увеличения эффективности решения задач классификации и предсказания поведения объектов наблюдения вызывает необходимость совершенствования методов обработки данных. В работе предлагается метод повышения показателей качества моделей машинного обучения в задачах регрессии и прогнозирования.</p></sec><sec><title>Метод</title><p>Метод. Предложенная обработка информационных последовательностей предполагает применение сегментации входных данных. В результате разделения данных образуются сегменты с различными свойствами объектов наблюдения. Новизна метода заключается в разделении последовательности на сегменты c использованием функционала качества моделей обработки на подвыборках данных. Это позволяет применять лучшие по качественным показателям модели на разных сегментах данных. Полученные сегменты являются отдельными подвыборками, на которые назначаются лучшие по качественным показателям модели и алгоритмы машинного обучения. Основные результаты. Для оценки качества предлагаемого решения выполнен эксперимент с использованием модельных данных и множественной регрессии. Рассчитанные значения показателя качества Root Mean Squared Error (RMSE) для выбранных алгоритмов на экспериментальной выборке и при различном количестве сегментов продемонстрировали повышение качественных показателей отдельных алгоритмов при увеличении количества сегментов. Предлагаемый метод позволяет повысить показатели RMSE в среднем на 7 % за счет сегментации и назначения моделей, которые имеют наилучшие показатели в отдельных сегментах. Обсуждение. Результаты метода могут применяться дополнительно при разработке моделей и методов обработки данных. Представленное решение направлено на дальнейшее усовершенствование и расширение ансамблевых методов. Формирование многоуровневых модельных структур, осуществляющих обработку, анализ поступающих информационных потоков и назначение наиболее подходящей модели для решения текущей задачи, позволяет уменьшить сложность и ресурсоемкость классических ансамблевых методов. В результате уменьшено влияние проблемы переобучения, снижена зависимость результатов обработки от базовых моделей, повышена оперативность настройки базовых алгоритмов в случае трансформации свойств данных и улучшена интерпретируемость результатов.</p></sec></abstract><trans-abstract xml:lang="en"><p>The constantly emerging need to increase the efficiency of solving classification problems and predicting the behavior of objects under observation necessitates improving data processing methods. This article proposes a method for improving the quality indicators of machine learning models in regression and forecasting problems. The proposed processing of information sequences involves the use of input data segmentation. As a result of data division, segments with different properties of observation objects are formed. The novelty of the method lies in dividing the sequence into segments using the quality functional of processing models on data subsamples. This allows you to apply the best quality models on various data segments. The segments obtained in this way are separate subsamples to which the best quality models and machine learning algorithms are assigned. To assess the quality of the proposed solution, an experiment was performed using model data and multiple regression. The obtained values of the quality indicator RMSE for various algorithms on an experimental sample and with a different number of segments demonstrated an increase in the quality indicators of individual algorithms with an increase in the number of segments. The proposed method can improve RMSE performance by an average of 7 % by segmenting and assigning models that have the best performance in individual segments. The results obtained can be additionally used in the development of models and data processing methods. The proposed solution is aimed at further improving and expanding ensemble methods. The formation of multi-level model structures that process, analyze incoming information flows and assign the most suitable model for solving the current problem makes it possible to reduce the complexity and resource intensity of classical ensemble methods. The impact of the overfitting problem is reduced, the dependence of processing results on the basic models is reduced, the efficiency of setting up basic algorithms in the event of transformation of data properties is increased, and the interpretability of the results is improved.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>информационная последовательность данных</kwd><kwd>многоуровневая модель обработки данных</kwd><kwd>сегментация данных</kwd><kwd>повышение показателей качества</kwd></kwd-group><kwd-group xml:lang="en"><kwd>information sequence of data</kwd><kwd>multi-level data processing model</kwd><kwd>data segmentation</kwd><kwd>improving quality indicators</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">Marques H.O., Swersky L., Sander J., Campello R., Zimek A. On the evaluation of outlier detection and one-class classification: a comparative study of algorithms, model selection, and ensembles // Data Mining and Knowledge Discovery. 2023. V. 37. N 4. P. 1473– 1517. https://doi.org/10.1007/s10618-023-00931-x</mixed-citation><mixed-citation xml:lang="en">Marques H.O., Swersky L., Sander J., Campello R., Zimek A. On the evaluation of outlier detection and one-class classification: a comparative study of algorithms, model selection, and ensembles. Data Mining and Knowledge Discovery, 2023, vol. 37, no. 4, pp. 1473–1517. https://doi.org/10.1007/s10618-023-00931-x</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Mishra S., Shaw K., Mishra D., Patil S., Kotecha K., Kumar S., Bajaj S. Improving the accuracy of ensemble machine learning classification models using a novel bit-fusion algorithm for healthcare AI systems // Frontiers in Public Health. 2022. V. 10. P. 1–17. https://doi.org/10.3389/fpubh.2022.858282</mixed-citation><mixed-citation xml:lang="en">Mishra S., Shaw K., Mishra D., Patil S., Kotecha K., Kumar S., Bajaj S. Improving the accuracy of ensemble machine learning classification models using a novel bit-fusion algorithm for healthcare AI systems. Frontiers in Public Health, 2022, vol. 10, pp. 1–17. https://doi.org/10.3389/fpubh.2022.858282</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Ren J., Tapert S., Fan C.C., Thompson W.K. A semi-parametric Bayesian model for semi-continuous longitudinal data // Statistics in Medicine. 2022. V. 41. N 13. P. 2354–2374. https://doi.org/10.1002/sim.9359</mixed-citation><mixed-citation xml:lang="en">Ren J., Tapert S., Fan C.C., Thompson W.K. A semi-parametric Bayesian model for semi-continuous longitudinal data. Statistics in Medicine, 2022, vol. 41, no. 13, pp. 2354–2374. https://doi.org/10.1002/sim.9359</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang Y., Liu J., Shen W. A review of ensemble learning algorithms used in remote sensing applications // Applied Sciences. 2022. V. 12. N 17. P. 8654. https://doi.org/10.3390/app12178654</mixed-citation><mixed-citation xml:lang="en">Zhang Y., Liu J., Shen W. A review of ensemble learning algorithms used in remote sensing applications. Applied Sciences, 2022, vol. 12, no. 17, pp. 8654. https://doi.org/10.3390/app12178654</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Bellman R. On the approximation of curves by line segments using dynamic programming // Communications of the ACM. 1961. V. 4. N 6. P. 284–301. https://doi.org/10.1145/366573.366611</mixed-citation><mixed-citation xml:lang="en">Bellman R. On the approximation of curves by line segments using dynamic programming. Communications of the ACM, 1961, vol. 4, no. 6, pp. 284–301. https://doi.org/10.1145/366573.366611</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Page E. A test for a change in a parameter occurring at an unknown point // Biometrika. 1955. V. 42. N 3/4. P. 523–527. https://doi.org/10.2307/2333401</mixed-citation><mixed-citation xml:lang="en">Page E. A test for a change in a parameter occurring at an unknown point. Biometrika, 1955, vol. 42, no. 3/4, pp. 523–527. https://doi.org/10.2307/2333401</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Fisher W.D. On grouping for maximum homogeneity // Journal of the American Statistical Association. 1958. V. 53. N 284. P. 789–798. https://doi.org/10.1080/01621459.1958.10501479</mixed-citation><mixed-citation xml:lang="en">Fisher W.D. On grouping for maximum homogeneity. Journal of the American Statistical Association, 1958, vol. 53, no. 284, pp. 789–798. https://doi.org/10.1080/01621459.1958.10501479</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Melnyk I., Banerjee A. A spectral algorithm for inference in hidden semi-Markov models // Journal of Machine Learning Research. 2017. V. 18. N 35. P. 1–39.</mixed-citation><mixed-citation xml:lang="en">Melnyk I., Banerjee A. A spectral algorithm for inference in hidden semi-Markov models. Journal of Machine Learning Research, 2017, vol. 18, no. 35, pp. 1–39.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Bardwell L., Fearnhead P. Bayesian detection of abnormal segments in multiple time series // Bayesian Analysis. 2017. V. 12. N 1. P. 193– 218. https://doi.org/10.1214/16-ba998</mixed-citation><mixed-citation xml:lang="en">Bardwell L., Fearnhead P. Bayesian detection of abnormal segments in multiple time series. Bayesian Analysis, 2017, vol. 12, no. 1, pp. 193–218. https://doi.org/10.1214/16-ba998</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Chung F.-L., Fu T.-C., Ng V., Luk R.W.P. An evolutionary approach to pattern-based time series segmentation // IEEE Transactions on Evolutionary Computation. 2004. V. 8. N 5. P. 471–489. https://doi.org/10.1109/tevc.2004.832863</mixed-citation><mixed-citation xml:lang="en">Chung F.-L., Fu T.-C., Ng V., Luk R.W.P. An evolutionary approach to pattern-based time series segmentation. IEEE Transactions on Evolutionary Computation, 2004, vol. 8, no. 5, pp. 471–489. https:// doi.org/10.1109/tevc.2004.832863</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Levchenko O., Kolev B., Yagoubi D.E., Akbarinia R., Masseglia F., Palpanas T., Shasha D., Valduriez P. BestNeighbor: efficient evaluation of kNN queries on large time series databases // Knowledge and Information Systems. 2020. V. 63. N 2. P. 349–378. https://doi.org/10.1007/s10115-020-01518-4</mixed-citation><mixed-citation xml:lang="en">Levchenko O., Kolev B., Yagoubi D.E., Akbarinia R., Masseglia F., Palpanas T., Shasha D., Valduriez P. BestNeighbor: efficient evaluation of kNN queries on large time series databases. Knowledge and Information Systems, 2020, vol. 63, no. 2, pp. 349–378. https://doi.org/10.1007/s10115-020-01518-4</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Nikolaou A., Gutiérrez P.A., Durán A., Dicaire I., FernándezNavarro F., Hervás-Martínez C. Detection of early warning signals in paleoclimate data using a genetic time series segmentation algorithm // Climate Dynamics. 2015. V. 44. N 7. P. 1919–1933. https://doi.org/10.1007/s00382-014-2405-0</mixed-citation><mixed-citation xml:lang="en">Nikolaou A., Gutiérrez P.A., Durán A., Dicaire I., FernándezNavarro F., Hervás-Martínez C. Detection of early warning signals in paleoclimate data using a genetic time series segmentation algorithm. Climate Dynamics, 2015, vol. 44, no. 7, pp. 1919–1933. https://doi.org/10.1007/s00382-014-2405-0</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Liu N., Zhao J. Streaming data classification based on hierarchical concept drift and online ensemble // IEEE Access. 2023. V. 11. P. 126040–126051. https://doi.org/10.1109/access.2023.3327637</mixed-citation><mixed-citation xml:lang="en">Liu N., Zhao J. Streaming data classification based on hierarchical concept drift and online ensemble. IEEE Access, 2023, vol. 11, pp. 126040–126051. https://doi.org/10.1109/access.2023.3327637</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Zhong G., Shu T., Huang G., Yan X. Multi-view spectral clustering by simultaneous consensus graph learning and discretization // Knowledge-Based Systems. 2022. V. 235. P. 107632. https://doi.org/10.1016/j.knosys.2021.107632</mixed-citation><mixed-citation xml:lang="en">Zhong G., Shu T., Huang G., Yan X. Multi-view spectral clustering by simultaneous consensus graph learning and discretization. Knowledge-Based Systems, 2022, vol. 235, pp. 107632. https://doi.org/10.1016/j.knosys.2021.107632</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Liakos P., Papakonstantinopoulou K., Kotidis Y. Chimp: efficient lossless floating point compression for time series databases // Proceedings of the VLDB Endowment. 2022. V. 15. N 11. P. 3058–3070. https://doi.org/10.14778/3551793.3551852</mixed-citation><mixed-citation xml:lang="en">Liakos P., Papakonstantinopoulou K., Kotidis Y. Chimp: efficient lossless floating point compression for time series databases. Proceedings of the VLDB Endowment, 2022, vol. 15, no. 11, pp. 3058–3070. https://doi.org/10.14778/3551793.3551852</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Лебедев И.С. Сегментирование множества данных с учетом информации воздействующих факторов // Информационноуправляющие системы. 2021. № 3(112). С. 29–38. https://doi.org/10.31799/1684-8853-2021-3-29-38</mixed-citation><mixed-citation xml:lang="en">Lebedev I. Dataset segmentation considering the information about impact factors. Information and Control Systems, 2021, no. 3(112), pp. 29–38. (in Russian). https://doi.org/10.31799/1684-8853-2021-329-38</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Мальцев Г.Н., Якимов В.Л. Подход к формированию обобщенных параметров технического состояния сложных технических систем c использованием нейросетевых структур // Научнотехнический вестник информационных технологий, механики и оптики. 2023. Т. 23. № 4. С. 828–835. https://doi.org/10.17586/22261494-2023-23-4-828-835</mixed-citation><mixed-citation xml:lang="en">Maltsev G.N., Yakimov V.L. Approach to the generalized parameters formation of the complex technical systems technical condition using neural network structures. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2023, vol. 23, no. 4, pp. 828–835. (in Russian). https://doi.org/10.17586/22261494-2023-23-4-828-835</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Shili H. Clustering in big data analytics: a systematic review and comparative analysis (review article) // Научно-технический вестник информационных технологий, механики и оптики. 2023. Т. 23. № 5. С. 967–979. https://doi.org/10.17586/2226-1494-202323-5-967-979</mixed-citation><mixed-citation xml:lang="en">Shili H. Clustering in big data analytics: a systematic review and comparative analysis (review article). Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2023, vol. 23, no. 5, pp. 967–979. https://doi.org/10.17586/2226-14942023-23-5-967-979</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Lebedev I.S., Sukhoparov M.E. Adaptive Learning and integrated use of information flow forecasting methods // Emerging Science Journal. 2023. V. 7. N 3. P. 704–723. https://doi.org/10.28991/esj-2023-07-0303</mixed-citation><mixed-citation xml:lang="en">Lebedev I.S., Sukhoparov M.E. Adaptive Learning and integrated use of information flow forecasting methods. Emerging Science Journal, 2023, vol. 7, no. 3, pp. 704–723. https://doi.org/10.28991/esj-202307-03-03</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Tong W., Wang Y., Liu D. An adaptive clustering algorithm based on local-density peaks for imbalanced data without parameters // IEEE Transactions on Knowledge and Data Engineering. 2023. V. 35. N 4. P. 3419–3432. https://doi.org/10.1109/tkde.2021.3138962</mixed-citation><mixed-citation xml:lang="en">Tong W., Wang Y., Liu D. An adaptive clustering algorithm based on local-density peaks for imbalanced data without parameters. IEEE Transactions on Knowledge and Data Engineering, 2023, vol. 35, no. 4, pp. 3419–3432. https://doi.org/10.1109/tkde.2021.3138962</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Silva R.P., Zarpelão B.B., Cano A., Junior S.B. Time series segmentation based on stationarity analysis to improve new samples prediction // Sensors. 2021. V. 21. N 21. P. 7333. https://doi.org/10.3390/s21217333</mixed-citation><mixed-citation xml:lang="en">Silva R.P., Zarpelão B.B., Cano A., Junior S.B. Time series segmentation based on stationarity analysis to improve new samples prediction. Sensors, 2021, vol. 21, no. 21, pp. 7333. https://doi.org/10.3390/s21217333</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Barzegar V., Laflamme S., Hu C., Dodson J. Multi-time resolution ensemble LSTMs for enhanced feature extraction in high-rate time series // Sensors. 2021. V. 21. N 6. P. 1954. https://doi.org/10.3390/s21061954</mixed-citation><mixed-citation xml:lang="en">Barzegar V., Laflamme S., Hu C., Dodson J. Multi-time resolution ensemble LSTMs for enhanced feature extraction in high-rate time series. Sensors, 2021, vol. 21, no. 6, pp. 1954. https://doi.org/10.3390/s21061954</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Huang W., Ding N. Privacy-preserving support vector machines with flexible deployment and error correction // Lecture Notes in Computer Science. 2021. V. 13107. P. 242–262. https://doi.org/10.1007/978-3030-93206-0_15</mixed-citation><mixed-citation xml:lang="en">Huang W., Ding N. Privacy-preserving support vector machines with flexible deployment and error correction. Lecture Notes in Computer Science, 2021, vol. 13107, pp. 242–262. https://doi.org/10.1007/9783-030-93206-0_15</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang X., Wang M. Weighted random forest algorithm based on Bayesian algorithm // Journal of Physics: Conference Series. 2021. V. 1924. P. 012006. https://doi.org/10.1088/1742-6596/1924/1/012006</mixed-citation><mixed-citation xml:lang="en">Zhang X., Wang M. Weighted random forest algorithm based on Bayesian algorithm. Journal of Physics: Conference Series, 2021, vol. 1924 , pp. 012006 . https://doi.org/10.1088/17426596/1924/1/012006</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Di Franco G., Santurro M. Machine learning, artificial neural networks and social research // Quality &amp; Quantity. 2021. V. 55. N 3. P. 1007–1025. https://doi.org/10.1007/s11135-020-01037-y</mixed-citation><mixed-citation xml:lang="en">Di Franco G., Santurro M. Machine learning, artificial neural networks and social research. Quality &amp; Quantity, 2021, vol. 55, no. 3, pp. 1007–1025. https://doi.org/10.1007/s11135-020-01037-y</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Si S., Zhao J., Cai Z., Dui H. Recent advances in system reliability optimization driven by importance measures // Frontiers of Engineering Management. 2020. V. 7. N 3. P. 335–358. https://doi.org/10.1007/s42524-020-0112-6</mixed-citation><mixed-citation xml:lang="en">Si S., Zhao J., Cai Z., Dui H. Recent advances in system reliability optimization driven by importance measures. Frontiers of Engineering Management, 2020, vol. 7, no. 3, pp. 335–358. https://doi.org/10.1007/s42524-020-0112-6</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Xu S., Song Y., Hao X. A comparative study of shallow machine learning models and deep learning models for landslide susceptibility assessment based on imbalanced data // Forests. 2022. V. 13. N 11. P. 1908. https://doi.org/10.3390/f13111908</mixed-citation><mixed-citation xml:lang="en">Xu S., Song Y., Hao X. A comparative study of shallow machine learning models and deep learning models for landslide susceptibility assessment based on imbalanced data. Forests, 2022, vol. 13, no. 11, pp. 1908. https://doi.org/10.3390/f13111908</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>
