<?xml version='1.0' encoding='utf-8'?>
<article xmlns:ns0="http://www.w3.org/1999/xlink" 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" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="ru">
 <front>
 <journal-meta>
 <journal-id journal-id-type="publisher-id">dongu-nec.ru</journal-id>
 <journal-title-group>
 <journal-title xml:lang="ru">Новое в экономической кибернетике</journal-title>
 <trans-title-group xml:lang="en">
 <trans-title>New in Economic Cybernetics</trans-title>
 </trans-title-group>
 </journal-title-group>
 <issn publication-format="electronic">2523-448X</issn>
 </journal-meta>
 <article-meta>
 <article-id pub-id-type="publisher-id">500</article-id>
 <article-id pub-id-type="doi">10.5281/zenodo.19231078</article-id>
 <article-categories>
 <subj-group subj-group-type="toc-heading" xml:lang="en">
 <subject>Articles</subject>
 </subj-group>
 <subj-group subj-group-type="toc-heading" xml:lang="ru">
 <subject>Статьи</subject>
 </subj-group>
 <subj-group subj-group-type="article-type">
 <subject>Research Article</subject>
 </subj-group>
 </article-categories>
 <title-group>
 <article-title xml:lang="en">DYNAMIC TIME SCALE TRANSFORMATION METHOD EFFICIENCY INCREASING FOR TIME SERIES CLUSTERING</article-title>
 <trans-title-group xml:lang="ru">
 <trans-title>ПОВЫШЕНИЕ ЭФФЕКТИВНОСТИ ПРИМЕНЕНИЯ МЕТОДА ДИНАМИЧЕСКОЙ ТРАНСФОРМАЦИИ ВРЕМЕННОЙ ШКАЛЫ ДЛЯ КЛАСТЕРИЗАЦИИ ВРЕМЕННЫХ РЯДОВ</trans-title>
 </trans-title-group>
 </title-group>
 <contrib-group>
 <contrib contrib-type="author">
 <contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-8790-6961</contrib-id>
 <name-alternatives>
 <name xml:lang="en">
 <surname>Kislyakov</surname>
 <given-names>Alexey</given-names>
 </name>
 <name xml:lang="ru">
 <surname>Кисляков</surname>
 <given-names>Алексей Николаевич</given-names>
 </name>
 </name-alternatives>
 <email>ankislyakov@mail.ru</email>
 <xref ref-type="aff" rid="aff1">1</xref>
 </contrib>
 </contrib-group>
 <aff-alternatives id="aff1">
 <aff xml:lang="ru">
 <institution>ФГБОУ ВО «Владимирский филиал Российской академии народного хозяйства и государственной службы при Президенте Российской Федерации»</institution>
 </aff>
 <aff xml:lang="en">
 <institution>Russian Academy of National Economy and Public Administration under the President of the Russian Federation</institution>
 </aff>
 </aff-alternatives>
 <pub-date date-type="pub" iso-8601-date="2026-05-31" publication-format="electronic">
 <day>31</day>
 <month>05</month>
 <year>2026</year>
 </pub-date>
 <issue>1</issue>
 <issue-title xml:lang="en">NO1 (2026)</issue-title>
 <issue-title xml:lang="ru">№1 (2026)</issue-title>
 <fpage>28</fpage>
 <lpage>40</lpage>
 <history>
 <date date-type="received" iso-8601-date="2026-06-26">
 <day>26</day>
 <month>06</month>
 <year>2026</year>
 </date>
 </history>
 <permissions>
 <copyright-statement xml:lang="ru">Copyright ©; 2026, Новое в экономической кибернетике</copyright-statement>
 <copyright-statement xml:lang="en">Copyright ©; 2026, New in Economic Cybernetics</copyright-statement>
 <copyright-year>2026</copyright-year>
 <copyright-holder xml:lang="ru">Новое в экономической кибернетике</copyright-holder>
 <copyright-holder xml:lang="en">New in Economic Cybernetics</copyright-holder>
 <license license-type="open-access" ns0:href="https://creativecommons.org/licenses/by-nc/4.0/" xml:lang="ru">
 <license-p>Эта статья распространяется на условиях лицензии Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)</license-p>
 </license>
 <license license-type="open-access" ns0:href="https://creativecommons.org/licenses/by-nc/4.0/" xml:lang="en">
 <license-p>This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)</license-p>
 </license>
 <ali:free_to_read />
 </permissions>
 <self-uri ns0:href="https://dongu-nec.ru/index.php/nec/article/view/500">https://dongu-nec.ru/index.php/nec/article/view/500</self-uri>
 <abstract xml:lang="en">
 <p>The article is devoted to the topical issue of improving the efficiency of time series clustering algorithms. The relevance of the work is due not only to the need to process growing amounts of information from areas such as finance, the Internet of Things, bioinformatics, and monitoring of industrial equipment, but also to the need for a deeper understanding of the hidden structure of this data. The aim of the study is to systematically improve the understanding of the internal structure of time series and, as a result, to develop more accurate, stable and computationally efficient algorithms for their cluster analysis. As a methodological basis, a comprehensive analysis of modern clustering methods is carried out, focusing on two key aspects: the assessment of structural similarities between series and techniques for decomposing time series into composite components (trend, seasonality, noise). Special attention is paid to the critically important issue of choosing an adequate distance metric, since the quality and interpretability of the final clusters directly depends on it. The potential and limitations of the metric of dynamic transformation of the time scale (DTW), capable of taking into account nonlinear distortions along the time axis, are investigated in detail. The main theoretical contribution of the article is to propose and justify hybrid approaches that integrate classical clustering algorithms (such as K-means or hierarchical clustering) based on the DTW metric with advanced methods of nonlinear dimensionality reduction, in particular, with the Uniform Manifold Approximation and Projection (UMAP) algorithm. This combination allows you to visualize and cluster data in a low-dimensional space that preserves significant geometric relationships, which improves the quality of grouping and the speed of calculations. In addition, the paper separately discusses strategies for optimizing the processing of long time series aimed at reducing computational complexity without significant loss of information content. The practical value of the research is confirmed by a series of computational experiments on synthetic and real datasets. The presented results clearly demonstrate the comparative advantages of the proposed hybrid techniques over traditional approaches in terms of clustering accuracy, noise tolerance, and computational efficiency. Thus, the work makes a significant contribution to the development of time series mining methods, offering new, more powerful tools for extracting knowledge from data.</p>
 </abstract>
 <trans-abstract xml:lang="ru">
 <p>Статья посвящена актуальной проблематике повышения эффективности алгоритмов кластеризации временных рядов. Актуальность работы обусловлена не только необходимостью обработки растущих объемов информации из таких сфер, как финансы, интернет вещей, биоинформатика и мониторинг промышленного оборудования, но и потребностью в более глубоком понимании скрытой структуры этих данных. Цель исследования заключается в системном улучшении понимания внутренней структуры временных рядов и, как следствие, в разработке более точных, устойчивых и вычислительно эффективных алгоритмов для их кластерного анализа. В качестве методологической основы проводится всесторонний анализ современных методов кластеризации, акцентирующий внимание на двух ключевых аспектах: оценке структурных сходств между рядами и техниках декомпозиции временных рядов на составные компоненты (тренд, сезонность, шум). Особое внимание в работе уделяется критически важному вопросу выбора адекватной метрики расстояния, поскольку от нее напрямую зависит качество и интерпретируемость итоговых кластеров. Детально исследуется потенциал и ограничения метрики динамической трансформации временной шкалы (DTW), способной учитывать нелинейные искажения по временной оси. Основной теоретический вклад статьи заключается в предложении и обосновании гибридных подходов, которые интегрируют классические алгоритмы кластеризации (такие как K‑средних или иерархическая кластеризация), основанные на метрике DTW, с передовыми методами нелинейного снижения размерности, в частности, с алгоритмом Uniform Manifold Approximation and Projection (UMAP). Такая комбинация позволяет визуализировать и кластеризовать данные в низкоразмерном пространстве, сохраняющем существенные геометрические отношения, что повышает качество группировки и скорость вычислений. Кроме того, в работе отдельно рассматриваются стратегии оптимизации обработки длинных временных рядов, направленные на снижение вычислительной сложности без значительной потери информативности. Практическая ценность исследования подтверждается серией вычислительных экспериментов на синтетических и реальных наборах данных. Представленные результаты наглядно демонстрируют сравнительные преимущества предложенных гибридных методик перед традиционными подходами в терминах точности кластеризации, устойчивости к шуму и вычислительной эффективности. Таким образом, работа вносит значимый вклад в развитие методов интеллектуального анализа временных рядов, предлагая новые, более мощные инструменты для извлечения знаний из данных.</p>
 </trans-abstract>
 <kwd-group xml:lang="ru">
 <kwd>кластеризация временных рядов, динамическая трансформация временной шкалы, понижение размерности, гибридные методы, машинное обучение.</kwd>
 </kwd-group>
 <funding-group>
 <funding-statement xml:lang="ru">time series clustering, dynamic time scale transformation, dimensionality reduction, hybrid methods, machine learning.</funding-statement>
 </funding-group>
 </article-meta>
 </front>
 <body>
 <p>[Полный текст статьи отсутствует в исходных данных. Необходимо добавить текст из PDF или другого источника.]</p>
 </body>
 <back>
 <ref-list>
 <title>Список литературы</title>
 <ref id="B1">
 <mixed-citation>1. Peker K. Subsequence time series (STS) clustering techniques for meaningful pattern discovery. 2005. 360 - 365. 10.1109/KIMAS.2005.1427109.</mixed-citation>
 </ref>
 <ref id="B2">
 <mixed-citation>2. Jain A.K. Data Clustering: 50 Years Beyond K-Means. Pattern Recognition Letters, 2010. 31(8), 651-666.</mixed-citation>
 </ref>
 <ref id="B3">
 <mixed-citation>3. Murtagh F. Methods of Hierarchical Clustering / F. Murtagh, P. Contreras // ArXiv. 2011. pp. 1-21. URL: https://arxiv.org/pdf/1105.0121.pdf (дата обращения: 27.01.2025).</mixed-citation>
 </ref>
 <ref id="B4">
 <mixed-citation>4. Giorgino T. Computing and Visualizing Dynamic Time Warping Alignments in R: The Dtw Package. Journal of Statistical Software. 2009. 31 (7). 1-24.</mixed-citation>
 </ref>
 <ref id="B5">
 <mixed-citation>5. Kislyakov A., Tikhonuyk N. Principles for Development of Predictive Stability Models of Social and Economic Systems on the basis of DTW // First Conference on Sustainable Develop-ment: Industrial Future of Territories (IFT 2020), 2020. vol. 208, no 08001. DOI: 10.1051/e3sconf/202020808001.</mixed-citation>
 </ref>
 <ref id="B6">
 <mixed-citation>6. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Second Edition // Publisher: Springer, 2017. 745 р.</mixed-citation>
 </ref>
 <ref id="B7">
 <mixed-citation>7. Draganov A., Jørgensen J. Nellemann K., Mottin D., Assent I. Berry T., Aslay C. ActUp: Analyzing and Consolidating tSNE and UMAP. 2023. 10.48550/arXiv.2305.07320.</mixed-citation>
 </ref>
 <ref id="B8">
 <mixed-citation>8. Aghabozorgi S., Seyed Shirkhorshidi A., Wah T. Y. Time-series clustering – A decade review // Information Systems. 2015. Vol. 53. pp. 16-38.</mixed-citation>
 </ref>
 <ref id="B9">
 <mixed-citation>9. Schwenke L., Atzmueller M. Making Time Series Embeddings More Interpretable in Deep Learning: Extracting Higher-Level Features via Symbolic Approximation Representations. The International FLAIRS Conference Proceedings. 2023. 36 p. 10.32473/flairs.36.133107.</mixed-citation>
 </ref>
 <ref id="B10">
 <mixed-citation>10. Serrà, J., Arcos J.L. A Competitive Measure to Assess the Similarity between Two Time Series. In: Agudo, B.D., Watson, I. (eds) Case-Based Reasoning Research and Development. ICCBR 2012. Lecture Notes in Computer Science, 2012. vol 7466. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32986-9_31.</mixed-citation>
 </ref>
 <ref id="B11">
 <mixed-citation>11. Sakoe H., Chiba S. Dynamic programming algorithm optimization for spoken word recognition. // Transactions on ASSP. 1978. № 26. P. 43-49.</mixed-citation>
 </ref>
 <ref id="B12">
 <mixed-citation>12. Salvador S., Chan P. Toward Accurate Dynamic Time Warping in Linear Time and Space. Intelligent Data Analysis. 2004. 11. 70-80.</mixed-citation>
 </ref>
 <ref id="B13">
 <mixed-citation>13. Keogh E. Exact indexing of dynamic time warping. In 28th International Conference on Very Large Data Bases. Hong Kong. 2002. pp 406-417.</mixed-citation>
 </ref>
 <ref id="B14">
 <mixed-citation>14. McInnes L., Healy J., Melville J. Umap: Uniform manifold aProximation and projection for dimension reduction, 2018. //arXiv preprint arXiv:1802.03426.</mixed-citation>
 </ref>
 <ref id="B15">
 <mixed-citation>15. Becht E. et al. Dimensionality reduction for visualizing single-cell data using UMAP //Nature biotechnology, 2019, Т. 37, №. 1, P. 38-44.</mixed-citation>
 </ref>
 <ref id="B16">
 <mixed-citation>16. Kullback, S., Leibler R.A. On Information and Sufficiency. The Annals of Mathematical Statistics, 1951. 22(1), 79-86.</mixed-citation>
 </ref>
 <ref id="B17">
 <mixed-citation>17. Srivastava A. DTW+S: Shape-based Comparison of Time-series with Ordered Local Trend. 2023 10.48550/arXiv.2309.03579.</mixed-citation>
 </ref>
 <ref id="B18">
 <mixed-citation>18. Zhu Z., Peng Q., Guan X. A time series clustering method based on hypergraph partitioning. 2016. 27-31. 10.1109/PIC.2016.7949461.</mixed-citation>
 </ref>
 <ref id="B19">
 <mixed-citation>References</mixed-citation>
 </ref>
 <ref id="B20">
 <mixed-citation>1. Peker K. (2005) Subsequence time series (STS) clustering techniques for meaningful pattern discovery. 360 - 365. 10.1109/KIMAS.2005.1427109.</mixed-citation>
 </ref>
 <ref id="B21">
 <mixed-citation>2. Jain A.K. (2010) Data Clustering: 50 Years Beyond K-Means. Pattern Recognition Letters. 31(8), 651-666.</mixed-citation>
 </ref>
 <ref id="B22">
 <mixed-citation>3. Murtagh F. (2011) Methods of Hierarchical Clustering / F. Murtagh, P. Contreras // ArXiv, pp. 1-21. URL: https://arxiv.org/pdf/1105.0121.pdf (дата обращения: 27.01.2025).</mixed-citation>
 </ref>
 <ref id="B23">
 <mixed-citation>4. Giorgino T. (2009) Computing and Visualizing Dynamic Time Warping Alignments in R: The Dtw Package. Journal of Statistical Software, 31 (7). 1-24.</mixed-citation>
 </ref>
 <ref id="B24">
 <mixed-citation>5. Kislyakov A., Tikhonuyk N. (2020) Principles for Development of Predictive Stability Models of Social and Economic Systems on the basis of DTW // First Conference on Sustainable Develop-ment: Industrial Future of Territories (IFT 2020), vol. 208, no 08001. DOI: 10.1051/e3sconf/202020808001.</mixed-citation>
 </ref>
 <ref id="B25">
 <mixed-citation>6. Hastie T., Tibshirani R., Friedman J. (2017) The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Second Edition // Publisher: Springer, 745 р.</mixed-citation>
 </ref>
 <ref id="B26">
 <mixed-citation>7. Draganov A., Jørgensen J. Nellemann K., Mottin D., Assent I. Berry T., Aslay C. (2023) ActUp: Analyzing and Consolidating tSNE and UMAP. 10.48550/arXiv.2305.07320.</mixed-citation>
 </ref>
 <ref id="B27">
 <mixed-citation>8. Aghabozorgi S., Seyed Shirkhorshidi A., Wah T. Y. (2015) Time-series clustering - A decade review // Information Systems, Vol. 53. pp. 16-38.</mixed-citation>
 </ref>
 <ref id="B28">
 <mixed-citation>9. Schwenke L., Atzmueller M. (2023) Making Time Series Embeddings More Interpretable in Deep Learning: Extracting Higher-Level Features via Symbolic Approximation Representations. The International FLAIRS Conference Proceedings. 36 p. 10.32473/flairs.36.133107.</mixed-citation>
 </ref>
 <ref id="B29">
 <mixed-citation>10. Serrà, J., Arcos J.L. (2012) A Competitive Measure to Assess the Similarity between Two Time Series. In: Agudo, B.D., Watson, I. (eds) Case-Based Reasoning Research and Development. ICCBR 2012. Lecture Notes in Computer Science, vol 7466. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32986-9_31.</mixed-citation>
 </ref>
 <ref id="B30">
 <mixed-citation>11. Sakoe H., Chiba S. (1978) Dynamic programming algorithm optimization for spoken word recognition. // Transactions on ASSP, № 26. P. 43-49.</mixed-citation>
 </ref>
 <ref id="B31">
 <mixed-citation>12. Salvador S., Chan P. (2004) Toward Accurate Dynamic Time Warping in Linear Time and Space. Intelligent Data Analysis, 11. 70-80.</mixed-citation>
 </ref>
 <ref id="B32">
 <mixed-citation>13. Keogh E. (2002) Exact indexing of dynamic time warping. In 28th International Conference on Very Large Data Bases. Hong Kong, pp 406-417.</mixed-citation>
 </ref>
 <ref id="B33">
 <mixed-citation>14. McInnes L., Healy J., Melville J. (2018) Umap: Uniform manifold aProximation and projection for dimension reduction, 2018. //arXiv preprint arXiv:1802.03426.</mixed-citation>
 </ref>
 <ref id="B34">
 <mixed-citation>15. Becht E. et al. (2019) Dimensionality reduction for visualizing single-cell data using UMAP //Nature biotechnology, Т. 37, №. 1, P. 38-44.</mixed-citation>
 </ref>
 <ref id="B35">
 <mixed-citation>16. Kullback, S., Leibler R.A. (1951) On Information and Sufficiency. The Annals of Mathematical Statistics, 22(1), 79-86.</mixed-citation>
 </ref>
 <ref id="B36">
 <mixed-citation>17. Srivastava A. (2023) DTW+S: Shape-based Comparison of Time-series with Ordered Local Trend. 10.48550/arXiv.2309.03579.</mixed-citation>
 </ref>
 <ref id="B37">
 <mixed-citation>18. Zhu Z., Peng Q., Guan X. (2016) A time series clustering method based on hypergraph partitioning, pp. 27-31. 10.1109/PIC.2016.7949461.</mixed-citation>
 </ref>
 </ref-list>
 </back>
 </article>
