Neural Networks Detection of Low-Amplitude Components on ECG Using Modified Wavelet Transform

Authors

DOI:

https://doi.org/10.20535/RADAP.2024.97.46-57

Keywords:

electrocardiography, wavelet transform, late atrial potentials, late ventricular potentials, neural networks

Abstract

This study is devoted to identification of low amplitude components from ECG signals by different time-frequency analysis methods when main power spectrum falls on high-amplitude components. It was also analyzed the problem of choosing correct scale system for determination low-amplitude components on the scalogram by artificial intelligence models. As a result of the study, several modifications of the continuous wavelet transform were proposed. First modification was based on the use of a scaling function and a modified wavelet. Second modification was based on the use of cosine similarity at each iteration of convolution followed by the use of a scaling function. The main idea of the study was to modify the wavelet transform in such a way as to select the components which has the target amplitude and reduce all other components that complicate the neural networks analysis of the interested fragments of the signal. Also, possible procedures for signal restoring were proposed for preserving the effect of using scaling modifications. The testing of the proposed modified algorithms was carried out on the basis of artificially created signals as well as on the basis of real ECG signals with late potentials superimposed on them. Visual analysis of scalograms and signal reconstructions obtained using the modified wavelet transform showed that the modified wavelet transform is capable of extracting low-amplitude components from the signal with much greater spectral power than the transform without modifications. In addition, the ability of common neural network models to distinguish between cardiac cycles with and without late potentials was tested. As a result, it was found that models that were trained on scalograms obtained using a modified wavelet transform train faster and are less susceptible to local minima stucking. The results of classification of signals with and without late potentials based on trained neural network models showed that training using scalograms obtained on the base of a modified wavelet transform allows achieving 99% classification accuracy, which is 1-49% more than that using scalograms obtained on the base of on the classical wavelet transform.

References

References

Hu Y., Zhao Y., Liu J., Pang J., Zhang C., and Li P. (2020). An effective frequency-domain feature of atrial fibrillation based on time–frequency analysis. BMC Med. Inform. Decis. Making, Vol. 20, No. 1, DOI: 10.1186/s12911-020-01337-1.

Ceschi R., Gautier J.-L. (2017). Fourier Transform. CHAPTER 2 In: Fourier Analysis. Wiley, pp. 39-96, DOI: 10.1002/9781119388944.ch2.

Borisagar K. R., Thanki R. M., and Sedani B. S. (2018). Fourier Transform, Short-Time Fourier Transform, and Wavelet Transform. In: Speech Enhancement Techniques for Digital Hearing Aids. Springer International Publishing, pp. 63-74. DOI: 10.1007/978-3-319-96821-6_4.

Lyon D. (2009). The Discrete Fourier Transform, Part 4: Spectral Leakage. J. Object Technol., Vol. 8, No. 7, p. 23. DOI: 10.5381/jot.2009.8.7.c2.

Athanassoulis A. G., Mauser N. J., and Paul T. (2009). Coarse-scale representations and smoothed Wigner transforms. J. de Mathématiques Pures et Appliquées, Vol. 91, No. 3, pp. 296-338. DOI: 10.1016/j.matpur.2009.01.001.

Addison P. S. (2005). Wavelet transforms and the ECG: a review. Physiol. Meas., Vol. 26, No. 5, pp. R155-R199. DOI: 10.1088/0967-3334/26/5/r01.

Saito D. et al. (2022). Atrial late potentials are associated with atrial fibrillation recurrence after catheter ablation. J. Arrhythmia, Vol. 38, Iss. 6, pp. 991-996. DOI: 10.1002/joa3.12786.

Prabhu K. M. M. (2018). Review of Window Functions. Chapter in: Window Functions and Their Applications in Signal Processing. CRC Press, pp. 87-127. DOI: 10.1201/9781315216386-3.

O'Toole J. M. and Boashash B. (2013). Fast and memory-efficient algorithms for computing quadratic time–frequency distributions. Appl. Comput. Harmon. Anal., Vol. 35, No. 2, pp. 350-358. DOI: 10.1016/j.acha.2013.01.003.

Tanaka T. and Mandic D. P. (2007). Complex Empirical Mode Decomposition. IEEE Signal Process. Lett., Vol. 14, No. 2, pp. 101-104. DOI: 10.1109/lsp.2006.882107.

Huang N., Wu Z., and Long S. (2008). Hilbert-Huang transform. Scholarpedia, Vol. 3, No. 7, p. 2544. DOI: 10.4249/scholarpedia.2544.

Hassani H. (2021). Singular Spectrum Analysis: Methodology and Comparison. J. Data Sci., Vol. 5, No. 2, pp. 239-257. DOI: 10.6339/jds.2007.05(2).396.

Li S., Ma S., and Wang S. (2023). Optimal Complex Morlet Wavelet Parameters for Quantitative Time-Frequency Analysis of Molecular Vibration. Appl. Sci., Vol. 13, No. 4, p. 2734. DOI: 10.3390/app13042734.

Vrhel M. J., Lee C., and Unser M. A. (1995). Fractal dimension estimation using the fast continuous wavelet transform. In SPIE's 1995 Int. Symp. Opt. Sci., Eng., Instrum., SPIE. DOI: 10.1117/12.217603.

Moody G. B. and Mark R. G. (1990). The MIT-BIH Arrhythmia Database on CD-ROM and software for use with it. In [1990] Comput. Cardiol., IEEE Computer Society Press. DOI: 10.1109/cic.1990.144205.

Wang X., Ma C., Zhang X., Gao H., Clifford G. D., and Liu C. (2021). Paroxysmal Atrial Fibrillation Events Detection from Dynamic ECG Recordings (version 1.0.0). PhysioNet. DOI: 10.13026/ksya-qw89.

Benesty J., Chen Jingdong, and Huang Yiteng (2008). On the Importance of the Pearson Correlation Coefficient in Noise Reduction. IEEE Trans. Audio, Speech, Lang. Process., Vol. 16, No. 4, pp. 757-765. DOI: 10.1109/tasl.2008.919072.

Chou E. P. and Hsu S.-M. (2018). Cosine similarity as a sample size-free measure to quantify phase clustering within a single neurophysiological signal. J. Neurosci. Methods, Vol. 295, pp. 111-120. DOI: 10.1016/j.jneumeth.2017.12.007.

Stojanovic M. et al. (2014). Understanding sensitivity, specificity and predictive values. Vojnosanit. Pregl., Vol. 71, No. 11, pp. 1062-1065. DOI: 10.2298/vsp1411062s.

Albardi F., Kabir H. M. D., Bhuiyan M. M. I., Kebria P. M., Khosravi A., and Nahavandi S. (2021). A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification. In 2021 IEEE Int. Conf. Syst., Man, Cybern. (SMC). DOI: 10.1109/smc52423.2021.9659161.

Lee H. K. and Choi Y.-S. (2019). Application of Continuous Wavelet Transform and Convolutional Neural Network in Decoding Motor Imagery Brain-Computer Interface. Entropy, Vol. 21, No. 12, p. 1199. DOI: 10.3390/e21121199.

Fagan X., Ivanko K., and Ivanushkina N. (2020). Detection of Ventricular Late Potentials in Electrocardiograms Using Machine Learning. In Advances in Computer Science for Engineering and Education III, Springer International Publishing, pp. 487-497. DOI: 10.1007/978-3-030-55506-1_44.

Kalidas V. and Tamil L. (2017). Real-time QRS detector using Stationary Wavelet Transform for Automated ECG Analysis. 2017 IEEE 17th Int. Conf. Bioinf. Bioeng. (BIBE), IEEE. DOI: 10.1109/bibe.2017.00-12.

Kingma D. P. and Ba J. (2014). Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs.LG]. DOI: 10.48550/arXiv.1412.6980.

Downloads

Published

2024-09-30

How to Cite

Mnevets , A. V. and Ivanushkina, N. G. (2024) “Neural Networks Detection of Low-Amplitude Components on ECG Using Modified Wavelet Transform”, Visnyk NTUU KPI Seriia - Radiotekhnika Radioaparatobuduvannia, (97), pp. 46-57. doi: 10.20535/RADAP.2024.97.46-57.

Issue

Section

Radioelectronics Medical Technologies