<?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">caht</journal-id><journal-title-group><journal-title xml:lang="ru">Научный вестник МГТУ ГА</journal-title><trans-title-group xml:lang="en"><trans-title>Civil Aviation High Technologies</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2079-0619</issn><issn pub-type="epub">2542-0119</issn><publisher><publisher-name>Moscow State Technical University of Civil Aviation (MSTU CA)</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.26467/2079-0619-2024-27-4-34-49</article-id><article-id custom-type="elpub" pub-id-type="custom">caht-2400</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>ТРАНСПОРТНЫЕ СИСТЕМЫ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>TRANSPORTATION SYSTEMS</subject></subj-group></article-categories><title-group><article-title>Метод выявления актуальных тем тренажерной подготовки пилотов на основе кластеризации отчетов по безопасности полетов</article-title><trans-title-group xml:lang="en"><trans-title>A method for identifying relevant topics of pilot simulator training based on clustering of flight safety reports</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>Заббаров</surname><given-names>З. Р.</given-names></name><name name-style="western" xml:lang="en"><surname>Zabbarov</surname><given-names>Z. R.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Заббаров Зульфат Рифкатович, аспирант;</p><p>Пилот</p><p>г. Москва;</p><p>г. Ульяновск</p></bio><bio xml:lang="en"><p>Zulfat R. Zabbarov, Postgraduate Student;</p><p>Pilot</p><p>Moscow;</p><p>Ulyanovsk</p></bio><email xlink:type="simple">zabbarovz@gmail.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>Волков</surname><given-names>А. К.</given-names></name><name name-style="western" xml:lang="en"><surname>Volkov</surname><given-names>A. K.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Волков Александр Константинович, кандидат технических наук, доцент, доцент кафедры обеспечения авиационной безопасности</p><p>г. Ульяновск</p></bio><bio xml:lang="en"><p>Alexander K. Volkov, Сandidate of Technical Sciences, Assistant Professor, Assistant Professor at the Department of Aviation Security</p><p>Ulyanovsk</p></bio><email xlink:type="simple">volkovalex8@rambler.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ПАО «Аэрофлот – российские авиалинии»;&#13;
Ульяновский институт гражданской авиации имени Главного маршала авиации Б.П. Бугаева</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Public Joint Stock Company “Aeroflot – Russian Airlines”;&#13;
Ulyanovsk Civil Aviation Institute named after Air Chief Marshal B.P. Bugaev</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Ульяновский институт гражданской авиации имени Главного маршала авиации Б.П. Бугаева</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Ulyanovsk Civil Aviation Institute named after Air Chief Marshal B.P. Bugaev</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>29</day><month>08</month><year>2024</year></pub-date><volume>27</volume><issue>4</issue><fpage>34</fpage><lpage>49</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Заббаров З.Р., Волков А.К., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Заббаров З.Р., Волков А.К.</copyright-holder><copyright-holder xml:lang="en">Zabbarov Z.R., Volkov A.K.</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://avia.mstuca.ru/jour/article/view/2400">https://avia.mstuca.ru/jour/article/view/2400</self-uri><abstract><p>Технологии обработки естественного языка (natural language processing – NLP) в одном из своих применений обеспечивают эффективное исследование закономерностей и тенденций в больших наборах текстовых данных. Текстовые данные по безопасности полетов, представленные в виде отчетов по расследованию авиационных происшествий, являются перспективным объектом для извлечения новой полезной информации, которую можно использовать как при управлении безопасностью полетов, так и в рамках тренажерной подготовки. В данной работе рассматриваются вопросы применения технологий NLP для исследования корпуса отчетов по безопасности полетов ПАО «Аэрофлот – российские авиалинии». Целью исследования является разработка метода выявления актуальных тем тренажерной подготовки пилотов. Представлен анализ существующих зарубежных исследований в области интеллектуального анализа текстовой информации в гражданской авиации. Выявлено, что за рубежом активно применяют технологии NLP для изучения отчетов по безопасности полетов. В статье представлена схема метода выявления актуальных тем тренажерной подготовки пилотов, основанного на кластеризации отчетов по безопасности полетов. Описаны процедуры предварительной обработки текста и построение его векторного пространства. Научной новизной подхода является то, что в отличие от предыдущих работ предлагается использовать полное векторное представление отчетов по безопасности полетов, которое строится объединением матриц тематических и семантических векторов. Проведена апробация предложенного метода. Анализируемый корпус текстов составил 1080 отчетов. В результате применения алгоритма кластеризации были идентифицированы 36 кластеров, которые затем были визуализированы с помощью алгоритма t-распределенного стохастического эмбеддинга соседей (t-distributed Stochastic Neighbor Embedding – t-SNE). Практическая значимость результатов исследования заключается в том, что подход, основанный на кластеризации отчетов, позволит проводить более глубокий анализ отчетов по безопасности полетов, что может упростить и ускорить работу как специалистов по управлению безопасностью полетов, так и инструкторов по тренажерной подготовке пилотов.</p></abstract><trans-abstract xml:lang="en"><p>Natural language processing (NLP) technologies, in one of their applications, provide effective research of patterns and trends in large sets of textual data. Textual safety data presented in the form of accident investigation reports is a promising object for extracting new useful information that can be used both in flight safety management and in the framework of simulator training. This paper discusses the application of NLP technologies for the study of the body of flight safety reports of PJSC Aeroflot – Russian Airlines. The aim of the work is to develop a method for identifying relevant topics of simulator training for pilots. The paper presents an analysis of existing foreign works in the field of intellectual analysis of textual information in civil aviation. It has been revealed that NLP technologies are actively used abroad to study flight safety reports. The paper presents a scheme of a method for identifying relevant topics of pilot simulator training based on clustering of flight safety reports. The procedures of text preprocessing and the construction of its vector space are described. The scientific novelty of the approach is that, unlike previous works, it is proposed to use a full vector representation of flight safety reports, which is built by combining matrices of thematic and semantic vectors. The proposed method has been tested. The analyzed corpus of texts amounted to 1080 reports. As a result of the clustering algorithm, 36 clusters were identified, which were then visualized using the algorithms t-distributed stochastic embedding of neighbors (t-SNE). The practical significance of the research results lies in the fact that the approach based on clustering of reports will allow for a more in-depth analysis of flight safety reports, which can simplify and speed up the work of both safety management specialists and flight simulator instructors.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>безопасность полетов</kwd><kwd>тренажерная подготовка</kwd><kwd>отчет</kwd><kwd>кластеризация</kwd><kwd>обработка естественного языка</kwd><kwd>тематическое моделирование</kwd><kwd>модель Doc2Vec</kwd></kwd-group><kwd-group xml:lang="en"><kwd>flight safety</kwd><kwd>simulator training</kwd><kwd>report</kwd><kwd>clustering</kwd><kwd>natural language processing</kwd><kwd>thematic modeling</kwd><kwd>Doc2Vec model</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">Groff L. Applying natural language processing tools to occurrence reports [Электронный ресурс] // ICAO, 2018. 20 p. URL: https://www.icao.int/safety/iStars/Documents/IUG%20Meeting%201/Presentations/Applying%20Natural%20Language%20Processing%20Tools%20to%20Occurrence%20Reports%20-%20Loren%20Groff.pdf (дата обращения: 20.01.2024).</mixed-citation><mixed-citation xml:lang="en">Groff, L. (2018). Applying natural language processing tools to occurrence reports. ICAO, 20 p. Available at: https://www.icao.int/safety/iStars/Documents/IUG%20Meeting%201/Presentations/Applying%20Natural%20Language%20Processing%20Tools%20to%20Occurrence%20Reports%20-%20Loren%20Groff.pdf (accessed: 20.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Junjie L., Huijuan Y., Yinlan D. Application of text analysis technology in aviation safety information analysis [Электронный ресурс] // Journal of Physics: Conference Series. 2020. Vol. 1624, no. 3. Pp. 032033. DOI: 10.1088/1742-6596/1624/3/032033 (дата обращения: 20.01.2024).</mixed-citation><mixed-citation xml:lang="en">Junjie, L., Huijuan, Y., Yinlan, D. (2020). Application of text analysis technology in aviation safety information analysis. Journal of Physics: Conference Series, vol. 1624. no. 3, pp. 032033. DOI: 10.1088/1742-6596/1624/3/032033 (accessed: 20.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Pimm C. Natural Language Processing (NLP) tools for the analysis of incident and accident reports / C. Pimm, C. Raynal, N. Tulechki, E. Hermann, G. Caudy [Электронный ресурс] // International Conference on HumanComputer Interaction in Aerospace (HCI-Aero). Belgium, Brussels, 2012. Pp. 1–7. URL: https://core.ac.uk/download/pdf/50536379.pdf (дата обращения: 20.01.2024).</mixed-citation><mixed-citation xml:lang="en">Pimm, C., Raynal, C., Tulechki, N., Hermann, E., Caudy, G. (2012). Natural Language Processing (NLP) tools for the analysis of incident and accident reports. In: International Conference on Human-Computer Interaction in Aerospace (HCI-Aero). Belgium, Brussels, pp. 1–7. Available at: https://core.ac.uk/download/pdf/50536379.pdf (accessed: 20.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Rose R.L., Puranik T.G., Mavris D.N. Natural language processing based method for clustering and analysis of aviation safety narratives [Электронный ресурс] // Aerospace. 2020. Vol. 7, no. 10. ID: 143. DOI: 10.3390/aerospace7100143 (дата обращения: 20.01.2024).</mixed-citation><mixed-citation xml:lang="en">Rose, R.L., Puranik, T.G., Mavris, D.N. (2020). Natural language processing based method for clustering and analysis of aviation safety narratives. Aerospace, vol. 7, no. 10, ID: 143. DOI: 10.3390/aerospace7100143 (accessed: 20.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Miyamoto A., Bendarkar M.V., Mavris D.N. Natural language processing of aviation safety reports to identify inefficient operational patterns [Электронный ресурс] // Aerospace. 2022. Vol. 9, no. 8. ID: 450. DOI: 10.3390/aerospace9080450 (дата обращения: 20.01.2024).</mixed-citation><mixed-citation xml:lang="en">Miyamoto, A., Bendarkar, M.V., Mavris, D.N. (2022). Natural language processing of aviation safety reports to identify inefficient operational patterns. Aerospace, vol. 9, no. 8. ID: 450. DOI: 10.3390/aerospace9080450 (accessed: 20.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Madeira T. Machine learning and natural language processing for prediction of human factors in aviation incident reports / T. Madeira, R. Melício, D. Valério, L. Santos [Электронный ресурс] // Aerospace. 2021. Vol. 8, no. 2. ID: 47. DOI: 10.3390/aerospace8020047 (дата обращения: 20.01.2024).</mixed-citation><mixed-citation xml:lang="en">Madeira, T., Rui, M., Duarte, V., Luis, S. (2021). Machine learning and natural language processing for prediction of human factors in aviation incident reports. Aerospace, vol. 8, no. 2. ID: 47. DOI: 10.3390/aerospace8020047 (accessed: 20.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Kuhn K.D. Using structural topic modeling to identify latent topics and trends in aviation incident reports // Transportation Research Part C-emerging Technologies. 2018. Vol. 87. Pp. 105–122. DOI: 10.1016/j.trc.2017.12.018</mixed-citation><mixed-citation xml:lang="en">Kuhn, K.D. (2018). Using structural topic modeling to identify latent topics and trends in aviation incident reports. Transportation Research Part C-emerging Technologies, vol. 87, pp. 105–122. DOI: 10.1016/j.trc.2017.12.018</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Switzer J., Khan L., Muhaya F.B. Subjectivity classification and analysis of the ASRS corpus [Электронный ресурс] // 2011 IEEE International Conference on Information Reuse &amp; Integration. USA, Las Vegas, NV, 2011. Pp. 160–165. DOI: 10.1109/IRI.2011.6009539 (дата обращения: 22.01.2024).</mixed-citation><mixed-citation xml:lang="en">Switzer, J., Khan, L., Muhaya, F.B. (2011). Subjectivity classification and analysis of the ASRS corpus. In: 2011 IEEE International Conference on Information Reuse &amp; Integration, USA, Las Vegas, NV, pp. 160–165. DOI: 10.1109/IRI.2011.6009539 (accessed: 22.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Ono M., Nakanishi M. Analysis of human factors and resilience competences in asrs data using natural language processing // Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. HCII 2023. Lecture Notes in Computer Science. 2023. Vol. 14029. Pp. 548–561. DOI: 10.1007/978-3-031-35748-0_37</mixed-citation><mixed-citation xml:lang="en">Ono, M., Nakanishi, M. (2023). Analysis of human factors and resilience competences in asrs data using natural language processing. Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. HCII 2023. Lecture Notes in Computer Science, vol. 14029, pp. 548–561. DOI: 10.1007/978-3-031-35748-0_37</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Blei D.M., Ng A.Y., Jordan M.I. Latent dirichlet allocation // The Journal of Machine Learning Research. 2003. Vol. 3. Pp. 993–1022.</mixed-citation><mixed-citation xml:lang="en">Blei, D.M., Ng, A.Y., Jordan, M.I. (2003). Latent dirichlet allocation. The Journal of Machine Learning Research, vol. 3, pp. 993–1022.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Мэрфи К.П. Вероятностное машинное обучение: введение / Пер. с англ. А.А. Слинкина. М.: ДМК Пресс, 2022. 990 с.</mixed-citation><mixed-citation xml:lang="en">Murphy, K.P. (2022). Probabilistic machine learning: An introduction. Boston: MIT Press, 864 p.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Ester M. A Density-based algorithm for discovering clusters in large spatial databases with Noise / M. Ester, H.P. Kriegel, J. Sander, X. Xu [Электронный ресурс] // Proceedings of 2nd International Conference on Knowledge Discovery and Data Mining (KDD-96), USA, Washington, DC, 1996. Pp. 1–6. URL: https://cs.fit.edu/~pkc/classes/ml-internet/papers/ester96kdd-dbscan.pdf (дата обращения: 23.01.2024).</mixed-citation><mixed-citation xml:lang="en">Ester, M., Kriegel, H.P., Sander, J., Xu, X. (1996). A Density-based algorithm for discovering clusters in large spatial databases with Noise. In: KDD-96, USA, Washington, DC, pp. 1–6. Available at: https://cs.fit.edu/~pkc/classes/ml-internet/papers/ester96kdd-dbscan.pdf (accessed: 23.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Nils H., Gampfer F., Buchkremer R. Latent dirichlet allocation and t-distributed stochastic neighbor embedding enhance scientific reading comprehension of articles related to enterprise architecture // AI. 2021. Vol. 2, no. 2. Pp. 179–194. DOI: 10.3390/ai2020011</mixed-citation><mixed-citation xml:lang="en">Nils, H., Gampfer, F., Buchkremer, R. (2021). Latent dirichlet allocation and tdistributed stochastic neighbor embedding enhance scientific reading comprehension of articles related to enterprise architecture. AI, vol. 2, no. 2, pp. 179–194. DOI: 10.3390/ai2020011</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Van Der Maaten L. Accelerating t-SNE using tree-based algorithms // Journal of Machine Learning Research. 2015. Vol. 15, Pp. 3221–3245.</mixed-citation><mixed-citation xml:lang="en">Van Der Maaten, L. (2015). Accelerating t-SNE using tree-based algorithms. Journal of Machine Learning Research, vol. 15, pp. 3221–3245.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Van der Maaten L., Hinton G.E. Visualizing high-dimensional data using t-SNE // Journal of Machine Learning Research. 2008. Vol. 9. Pp. 2579–2605.</mixed-citation><mixed-citation xml:lang="en">Van der Maaten, L., Hinton, G.E. (2008). Visualizing high-dimensional data using t-SNE. Journal of Machine Learning Research, vol. 9, pp. 2579–2605.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Коршунов А., Гомзин А. Тематическое моделирование текстов на естественном языке // Труды Института системного программирования РАН. 2012. № 23. С. 215–242. DOI: 10.15514/ISPRAS-2012-23-13</mixed-citation><mixed-citation xml:lang="en">Korshunov, A., Gomzin, A. (2012). Topic modeling in natural language texts. Trudy Instituta sistemnogo programmirovanija RAN, no. 23, pp. 215–242. DOI: 10.15514/ISPRAS2012-23-13 (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Slutsky A., Hu X., An Y. Tree labeled LDA: a hierarchical model for web summaries [Электронный ресурс] // Proceedings of the 2013 IEEE International Conference on Big Data. USA, Silicon Valley, CA, 2013. Pp. 134–140. DOI: 10.1109/BigData.2013.6691745 (дата обращения: 28.01.2024).</mixed-citation><mixed-citation xml:lang="en">Slutsky, A., Hu, X., An, Y. (2013). Tree labeled LDA: a hierarchical model for web summaries. In: Proceedings of the 2013 IEEE International Conference on Big Data, USA, Silicon Valley, CA, pp. 134–140. DOI: 10.1109/BigData.2013.6691745 (accessed: 28.01.2024).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Краснов Ф.В., Баскакова Е.Н., Смазневич И.С. Оценка прикладного качества тематических моделей для задач кластеризации // Вестник Томского государственного университета. Управление, вычислительная техника и информатика. 2021. № 56. С. 100–111. DOI: 10.17223/19988605/56/11</mixed-citation><mixed-citation xml:lang="en">Krasnov, F.V., Baskakova, E.N., Smaznevich I.S. (2020). Assessment of the applied quality of topic models for clustering problems. Tomsk State University Journal of Control and Computer Science, no. 56, pp. 100–111. DOI: 10.17223/19988605/56/11 (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Shaheen S., Marco R.S. Full-text or abstract? Examining topic coherence scores using Latent Dirichlet Allocation [Электронный ресурс] // 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA). Japan, Tokyo, 2017. Pp. 165–174. DOI: 10.1109/DSAA.2017.61 (дата обращения: 28.01.2024).</mixed-citation><mixed-citation xml:lang="en">Shaheen, S., Marco, R.S. (2017). Fulltext or abstract? Examining topic coherence scores using Latent Dirichlet Allocation. In: 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Japan, Tokyo, pp. 165–174. DOI: 10.1109/DSAA.2017.61 (accessed: 28.01.2024).</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>
