Development of a criterion for selecting the level of wavelet decomposition for QRS detection in electrocardiogram signals using energy and entropy
DOI:
https://doi.org/10.15276/opu.1.71.2025.18Keywords:
electrocardiogram, QRS detection, discrete wavelet transform, signal entropy, energy analysis, decomposition levelAbstract
Analysis of electrocardiographic (ECG) signals is one of the key areas of modern biomedical engineering, providing the possibility of early detection of cardiac disorders such as arrhythmias, ischemia, and other cardiovascular pathologies. The most informative segment of the ECG signal is the QRS complex, which reflects the electrical activity of the heart ventricles and serves as an important marker for medical diagnostics. This work proposes a approach to selecting the optimal wavelet decomposition level based on quantitative analysis of energy and entropy characteristics of the signal at each level. The aim of the study is to construct a formalized criterion of informativeness for decomposition levels and evaluate the effectiveness of different types of mother wavelets for the task of extracting QRS complexes from ECG signals. Within the study, signals from the open MIT-BIH Arrhythmia Database were analyzed, and values of energy, entropy, and their ratio were calculated for each level of discrete wavelet transform. The results indicate that levels with high energy contribution and low entropy best reflect the localization of QRS complexes. It was shown that the choice of mother wavelet type significantly affects the distribution of these characteristics. The Daubechies wavelet was found to be the most effective for automated QRS detection, particularly at levels d3–d5. The scientific novelty of the work lies in the integration of the energy-entropy approach into the automated process of decomposition level selection without expert involvement. The practical significance is in the potential implementation of this method in computer diagnostic systems to improve their accuracy, reliability, and adaptability to various types of biomedical signals.
Downloads
References
Daubechies, I. (1992). Ten Lectures on Wavelets. SIAM. DOI: https://doi.org/10.1137/1.9781611970104.
Singh, R., & Krishnan, S. M. (2023). A review on feature extraction and classification of ECG signals for health monitoring using machine learning and deep learning. Biomedical Engineering Online, 22, Article 66. DOI: https://doi.org/10.1186/s12938-023-01075-1.
Agrawal, P., Arun, V., & Basu, A. (2025). Artificial Neural Network Based ECG Feature Extraction Using Wavelet Transform. In Emerging Wireless Technologies and Sciences. ICEWTS 2024 (Vol. 2399, pp. 8–22). Springer, Cham. DOI: https://doi.org/10.1007/978-3-031-87886-2_2.
Li, T., & Zhou, M. (2016). ECG Classification Using Wavelet Packet Entropy and Random Forests. Entropy, 18(8), Article 285. DOI: https://doi.org/10.3390/e18080285.
Cornforth, D., Tarvainen, M. P., & Jelinek, H. F. (2013). Using Renyi entropy to detect early cardiac autonomic neuropathy. In Proceedings of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 5562–5565). DOI: https://doi.org/10.1109/EMBC.2013.6610810.
Rekik, S., & Ellouze, N. (2015). P-Wave Detection Combining Entropic Criterion and Wavelet Transform. Journal of Signal and Information Processing, 6(3), 217–226. DOI: https://doi.org/10.4236/jsip.2015.63020.
Lenis, G., Pilia, N., Oesterlein, T., Luik, A., Schmitt, C., & Dössel, O. (2016). P wave detection and delineation in the ECG based on the phase free stationary wavelet transform and using intracardiac atrial electrograms as reference. Biomedical Engineering / Biomedizinische Technik, 61(1), 37–56. DOI: https://doi.org/10.1515/bmt-2014-0161.
Xia, Y., Han, J., & Wang, K. (2015). Quick detection of QRS complexes and R-waves using a wavelet transform and K-means clustering. Biomedical Materials and Engineering, 26(Suppl 1), S1059–S1065. DOI: https://doi.org/10.3233/BME-151402.
Peng, Z., & Wang, G. (2017). Study on Optimal Selection of Wavelet Vanishing Moments for ECG Denoising. Scientific Reports, 7, Article 4564. DOI: https://doi.org/10.1038/s41598-017-04837-9.
Huan, Z., Kochan, V., Velychko, A., Cheredarchuk, N., Bilash, O., Boiko, N., & Bondarenko, Y. (2023). Haar Wavelet-Based Classification Method for Visual Information Processing Systems. Applied Sciences, 13(9), Article 5515. DOI: https://doi.org/10.3390/app13095515.
Addison, P. S. (2005). Wavelet transforms and the ECG: a review. Physiological Measurement, 26(5), R155–R199. DOI: https://doi.org/10.1088/0967-3334/26/5/R01.
Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C. K., & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation, 101(23), e215–e220. DOI: https://doi.org/10.1161/01.CIR.101.23.e215.
PhysioNet. (n.d.). MIT-BIH Arrhythmia Database. Retrieved from https://www.physionet.org/content/mitdb/1.0.0/. (Accessed: 12.05.2025).
Koshutina, D. V., & Shcherbakova, H. Yu. (2025). Automated Selection of Wavelet Decomposition Level Based on Energy and Entropy for QRS Complex Detection in ECG. In Modern Information Technologies – 2025: Proceedings of the 15th International Scientific Conference for Students and Young Scientists, May 15–16, 2025, Odesa, Ukraine (pp. 21–23). Nauka i Tekhnika. Retrieved from https://drive.google.com/file/d/1zi1TabIH7iso1-SW__9ntZ_LG0glE4Wa/view.
Ashiri, M., Lithgow, B., Suleiman, A., Mansouri, B., & Moussavi, Z. (2021). Electrovestibulography (EVestG) application for measuring vestibular response to horizontal pursuit and saccadic eye movements. Biocybernetics and Biomedical Engineering, 41(2), 527–539. DOI: https://doi.org/10.1016/j.bbe.2021.03.007.
Li, C., Zheng, C., & Tai, C. (1995). Detection of ECG characteristic points using wavelet transforms. IEEE Transactions on Biomedical Engineering, 42(1), 21–28. DOI: https://doi.org/10.1109/10.362922.
Liu, M., Song, Q., & Cao, Y. (2020). ECG classification based on improved wavelet threshold denoising and CNN. Computers in Biology and Medicine, 123, Article 103866. DOI: https://doi.org/10.1016/j.compbiomed.2020.103866.
Kligfield, P., Gettes, L. S., Bailey, A., Childers, R., Deal, B. J., Hancock, E. W., van Herpen, M., Karasik, P., Lloyd-Jones, D., Mason, J. W., Mirvis, D. M., Okin, P., Surawicz, B., Wagner, G. S., & Josephson, M. E. (2007). Recommendations for the Standardization and Interpretation of the Electrocardiogram. Journal of the American College of Cardiology, 49(10), 1109–1127. DOI: https://doi.org/10.1016/j.jacc.2007.01.024.
Widman, L. E., Yochim, M., & Jackson, K. (2022). ECG Criteria for Left and Right Bundle Branch Block: A Clinical Review. The American Journal of Medicine, 135(1), 1–9. DOI: https://doi.org/10.1016/j.amjmed.2021.08.028.
Jeyhani, V., Mahdiani, S., & Akhbardeh, A. (2021). Atrial Fibrillation Detection Using Shannon Entropy and Machine Learning Techniques. Computers in Biology and Medicine, 135, Article 104606. DOI: https://doi.org/10.1016/j.compbiomed.2021.104606.
