Please use this identifier to cite or link to this item: https://dspace.ncfu.ru/handle/20.500.12258/26634
Title: About the Choice of Data Balance Method for Neural Network Classification of Electrocardiogram Signals
Authors: Kiladze, M. R.
Киладзе, М. Р.
Kalita, D. I.
Калита, Д. И.
Lyakhova, U. A.
Ляхова, У. А.
Orazaev, A. R.
Оразаев, А. Р.
Keywords: BiLSTM;Computing in Cardiology Challenge 2017;Electrocardiogram;GRU;LSTM;Method ROS;Method SMOTE;PhysioNet
Issue Date: 2023
Citation: Kiladze, M.R., Kalita, D.I., Lyakhova, U.A., Orazaev, A.R. About the Choice of Data Balance Method for Neural Network Classification of Electrocardiogram Signals // Proceedings of the 2023 International Conference "Quality Management, Transport and Information Security, Information Technologies", IT and QM and IS 2023. - 2023. - pp. 133-136. - DOI: 10.1109/ITQMTIS58985.2023.10346399
Series/Report no.: Proceedings of the 2023 International Conference "Quality Management, Transport and Information Security, Information Technologies", IT and QM and IS 2023
Abstract: Diseases of the cardiovascular system are the main cause of death in the world population. Classification of electrocardiogram (ECG) signals is a reliable method for diagnosing cardiac pathologies. The available ECG databases consist of an unequal number of signals from various pathologies. This article analyzes the impact of using class alignment methods on the result of neural network classification of ECG signals. The results demonstrate that the SMOTE GRU algorithm provides high performance in classifying ECG segments, while the BiLSTM ROS algorithm provides high performance in classifying full ECG signals. The Accuracy, Loss, Recall, Precision, F-score values are respectively 70.31% and 77.73%, 0.29 and 0.41, 90.1% and 96.0%, 78.8% and 83.4%, 88.5% and 95.3%.
URI: http://hdl.handle.net/20.500.12258/26634
Appears in Collections:Статьи, проиндексированные в SCOPUS, WOS

Files in This Item:
File SizeFormat 
scopusresults 2966 .pdf
  Restricted Access
132.95 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.