Методи багаторівневого аналізу електрокардіографічних сигналів із застосуванням вейвлет-перетворень

V.I. Holota; V.O. Polinyayev; V.V. Martyniuk

doi:10.15330/itee.2024.1.04

Authors

V.I. Holota Vasyl Stefanyk Precarpathian National University https://orcid.org/0000-0003-4605-7507
V.O. Polinyayev Vasyl Stefanyk Precarpathian National University https://orcid.org/0009-0001-7413-0751
V.V. Martyniuk Vasyl Stefanyk Precarpathian National University https://orcid.org/0009-0001-4310-6302

DOI:

https://doi.org/10.15330/itee.2024.1.04

Keywords:

electrocardiogram, ECG, digital signal processing, convolutionary neural networks, machine learning, deep neural models

Abstract

The article presents the analyze and development of a software system for digital processing and automated classification of electrocardiogram (ECG) signals using artificial intelligence methods. It demonstrates the creation of ECG spectrograms with wavelet transforms and the application of a three-channel convolutional neural network for accurate pathology recognition. The system architecture, user interface, and workflow are described. Performance evaluation and comparative analysis of technical solutions confirm the reliability, efficiency, and practical applicability of the developed system for clinical use.

References

Mnevets, A.V., & Ivanushkina, N.G., “Neural Networks Detection of Low-Amplitude Components on ECG Using Modified Wavelet Transform,” Visnyk NTUU KPI Seriia - Radiotekhnika Radioaparatobuduvannia, no. 97, pp. 46–57, 2024. doi: https://doi.org/10.20535/RADAP.2024.97.46-57

Software for Statistical Processing and Modeling of a Set of Synchronously Registered Cardio Signals of Different Physical Nature / S. Lupenko et al. Computer Modeling and Intelligent Systems. 2021. Vol. 2864. P. 194–205. doi: https://doi.org/10.32782/cmis/2864-17.

Dzundza, B.S., Kohut, I.T., Holota, V.I., Fedoriuk, V.V., & Nykyruy, L.I., “Principles of Construction of Hybrid Microsystems for Biomedical Applications,” Physics and Chemistry of Solid State, vol. 23, no. 4, pp. 776–784, 2022. doi: https://doi.org/10.15330/pcss.23.4.776-784.

Electrocardiogram Classification Using Wavelet Transformations / I. Krak et al. 2020 IEEE 15th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), Lviv-Slavske, Ukraine, 25–29 February 2020. 2020. doi: https://doi.org/10.1109/tcset49122.2020.235573.

Lee J.-A., Kwak K.-C. Heart Sound Classification Using Wavelet Analysis Approaches and Ensemble of Deep Learning Models. Applied Sciences. 2023. Vol. 13, no. 21. P. 11942. doi: https://doi.org/10.3390/app132111942.

Modeling of integrated signal converters for biomedical sensor microsystems / I. T. Kogut et al. Physics and Chemistry of Solid State. 2023. Vol. 24, no. 3. P. 515–519. doi: https://doi.org/10.15330/pcss.24.3.515-519.

Electrocardiographic signal analysis using wavelet transforms / G. S. Kumari et al. 2015 International Conference on Electrical, Electronics, Signals, Communication and Optimization (EESCO), Visakhapatnam, 24–25 January 2015. 2015. doi: https://doi.org/10.1109/eesco.2015.7253688.

Cyber-physical System for Monitoring and Analyzing Human Biomedical Data / I. Kogut et al. Advances in Cyber-Physical Systems. 2024. Vol. 9, no. 1. P. 32–38. doi: https://doi.org/10.23939/acps2024.01.032.

Darsana P., Kumar V. N. Extracting Fetal ECG Signals through a Hybrid Technique Utilizing Two Wavelet-Based Denoising Algorithms. IEEE Access. 2023. P. 1. doi: https://doi.org/10.1109/access.2023.3308409.

Mostovoy Y. M., Danilevych T. D. Predictors of heart rhythm disorders in the patients with severe COVID-infection. Reports of Vinnytsia National Medical University. 2020. Vol. 24, no. 4. P. 640–646. URL: https://doi.org/10.31393/reports-vnmedical-2020-24(4)-14.