<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article 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="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Trudy NGTU im. R.E. Alekseeva</journal-id><journal-title-group><journal-title xml:lang="en">Trudy NGTU im. R.E. Alekseeva</journal-title><trans-title-group xml:lang="ru"><trans-title>Труды НГТУ им. Р.Е. Алексеева</trans-title></trans-title-group></journal-title-group><issn publication-format="print">1816-210X</issn><publisher><publisher-name xml:lang="en">Nizhny Novgorod State Technical University n.a. R.E. Alekseev</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">702232</article-id><article-id pub-id-type="doi">10.46960/1816-210X_2025_2_41</article-id><article-id pub-id-type="edn">HKDMOP</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>COMPUTER SCIENCE, MANAGEMENT AND SYSTEM ANALYSIS</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Информатика, управление и системный анализ</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">Preprocessing of ECG data and anomaly detection using recurrent neural networks</article-title><trans-title-group xml:lang="ru"><trans-title>Предобработка данных ЭКГ и обнаружение аномалий при помощи рекуррентных нейронных сетей</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1935-7697</contrib-id><name-alternatives><name xml:lang="en"><surname>Timofeeva</surname><given-names>O. P.</given-names></name><name xml:lang="ru"><surname>Тимофеева</surname><given-names>О. П.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><email>optimofeeva@mail.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-2450-0274</contrib-id><name-alternatives><name xml:lang="en"><surname>Gordeev</surname><given-names>M. M.</given-names></name><name xml:lang="ru"><surname>Гордеев</surname><given-names>М. М.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><email>maximgrdv@gmail.com</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Nizhny Novgorod State Technical University n.a. R.E. Alekseev</institution></aff><aff><institution xml:lang="ru">Нижегородский государственный технический университет им. Р.Е. Алексеева</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-06-21" publication-format="electronic"><day>21</day><month>06</month><year>2025</year></pub-date><issue>2</issue><issue-title xml:lang="en"/><issue-title xml:lang="ru"/><fpage>41</fpage><lpage>49</lpage><history><date date-type="received" iso-8601-date="2026-02-05"><day>05</day><month>02</month><year>2026</year></date><date date-type="accepted" iso-8601-date="2026-02-05"><day>05</day><month>02</month><year>2026</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Timofeeva O.P., Gordeev M.M.</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Тимофеева О.П., Гордеев М.М.</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Timofeeva O.P., Gordeev M.M.</copyright-holder><copyright-holder xml:lang="ru">Тимофеева О.П., Гордеев М.М.</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/"/><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://creativecommons.org/licenses/by/4.0</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.eco-vector.com/1816-210X/article/view/702232">https://journals.eco-vector.com/1816-210X/article/view/702232</self-uri><abstract xml:lang="en"><p>The paper considers the problem of detecting ECG anomalies using recurrent neural networks that can effectively process temporal dependencies of signals, as well as identify complex patterns and anomalies that may not be obvious when using traditional analysis methods. The stages of ECG data preprocessing from the ECG5000 dataset are described, including interpolation, augmentation and normalization of ECG in order to improve the characteristics of the input data for model training. The architecture of a neural network for solving the presented problem is presented, the process of its training and quality assessment is described. The obtained experimental results show high classification accuracy and the possibility of successfully identifying various types of anomalies. The prospects of using deep learning in the field of cardiology are substantiated, which can serve as a basis for further research.</p></abstract><trans-abstract xml:lang="ru"><p>Рассматривается задача обнаружения аномалий ЭКГ при помощи рекуррентных нейронных сетей, способных эффективно обрабатывать временные зависимости сигналов, а также выявлять сложные паттерны и аномалии, которые могут быть неочевидны при использовании традиционных методов анализа. Описываются этапы предобработки данных ЭКГ из датасета ECG5000, включая интерполяцию, аугментацию и нормализацию ЭКГ с целью улучшения характеристик входных данных для обучения модели. Представлена архитектура нейронной сети для решения поставленной задачи, изложен процесс ее обучения и оценки качества. Полученные результаты экспериментов показывают высокую точность классификации и возможность успешного выявления различных типов аномалий. Обоснована перспективность применения глубокого обучения в области кардиологии, что может послужить основой для проведения дальнейших исследований.</p></trans-abstract><kwd-group xml:lang="en"><kwd>data normalization</kwd><kwd>ECG classification</kwd><kwd>ECG anomaly detection</kwd><kwd>recurrent neural networks</kwd><kwd>ECG5000 dataset</kwd><kwd>web-service Django</kwd><kwd>quantization of model</kwd><kwd>data augmentation</kwd><kwd>inference optimization</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>нормализация данных</kwd><kwd>классификация ЭКГ</kwd><kwd>обнаружение аномалий ЭКГ</kwd><kwd>рекуррентные нейронные сети</kwd><kwd>датасет ECG5000</kwd><kwd>веб-сервис Django</kwd><kwd>квантизация модели</kwd><kwd>аугментация данных</kwd><kwd>оптимизация инференса</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Xu, H., Wu, G., Zhai, E., Jin, X., Tu, L. Preference-Aware Light Graph Convolution Network for Social Recommendation. Electronics 2023, 12, 2397.</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Alamr A., Artoli A. Unsupervised transformer-based anomaly detection in ECG signals. Algorithms. 2023. V. 16. № 3. Рр. 152.</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Ahmadi-Mobarakeh M., Mohammadzade H. ECG Classification Using DTW-Based Learnable Kernels in Deep Neural Networks. 2021 28th National and 6th International Iranian Conference on Biomedical Engineering (ICBME). IEEE, 2021. Рр. 90-94.</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Sabata T., Holena M. Active Learning for LSTM-autoencoder-based Anomaly Detection in Electrocardiogram Readings. IAL@PKDD/ECML. 2020. Рр. 72-77.</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Matias P. et al. Robust Anomaly Detection in Time Series through Variational AutoEncoders and a Local Similarity Score. Biosignals. 2021. Рр. 91-102.</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Peter A. Flach, Meelis Kull. Precision-Recall-Gain Curves: PR Analysis Done Right. Neural Information Processing Systems. 2015. Рр. 3-4.</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Y. Chen, T. Zhang, H. Wang, Y. Zhang, Y. Xu. Towards Accurate and Efficient Neural Network Quantization. IEEE Transactions on Neural Networks and Learning Systems. 2020. Рр. 1-12.</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Z. Wu, Y. Wang, Y. Zhang, L. Wang, Y. Wang. Quantization of Deep Neural Networks: A Survey. IEEE Transactions on Neural Networks and Learning Systems. 2018. Рр. 1-24.</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Z. Wu, Y. Wang, Y. Zhang, L. Wang, Y. Wang. Quantization of Deep Neural Networks: A Survey. IEEE Transactions on Neural Networks and Learning Systems. 2018. Рр. 1-24.</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Antonio Melé. Django 3 By Example: Build powerful web applications from scratch. Packt Publishing. 2020. Рр. 1-400.</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Adam Johnson. Django for APIs: Build web APIs with Python and Django. Independently published. 2018. Рр. 1-200.</mixed-citation></ref></ref-list></back></article>
