Abstract
This work presents a novel and robust automatic electrocardiogram (ECG) filtering system. The proposed filtering system allows an automatic selection of the adequate filter by applying the support vector machine (SVM). The SVM classification is based on an electrocardiogram feature vector that integrates four main input characteristics (maximum and minimum amplitudes, maximum frequency and power spectral density). This paper provides ECG denoising efficiency based on the automatic selection of three different competing filtering methods: the discrete wavelet transform (DWT), empirical mode decomposition (EMD) and the extended Kalman filter (EKF). The extensive simulations are performed by using the MIT-BIH database. The effectiveness of the proposed system is evaluated in term of signal-to-noise ratio (SNR) improvement in decibel (dB). The results showed that the proposed automatic ECG filtering system provided a better signal-to-noise ratio compared to the DWT, EMD or EKF algorithm alone. Therefore, an implementation of the proposed filtering system on graphical processing units (GPU) was realized to optimize execution time.
Similar content being viewed by others
Data availability
The dataset used in this article is available in ECG database at https://archive.physionet.org/physiobank/database/#ecg
References
M. Blanco-Velasco, B. Weng, K.E. Barner, ECG signal denoising and baseline wander correction based on the empirical mode decomposition. Comput. Biol. Med. 38(1), 1–13 (2008). https://doi.org/10.1016/j.compbiomed.2007.06.003
K.M. Chang, Arrhythmia ECG noise reduction by ensemble empirical mode decomposition. Sensors (Basel) 10(6), 6063–6080 (2010). https://doi.org/10.3390/s100606063
K.M. Chang, S.H. Liu, Gaussian noise filtering from ECG by wiener filter and ensemble empirical mode decomposition. J. Signal Process. Syst. 64(2), 249–264 (2011). https://doi.org/10.1007/s11265-009-0447-z
P. Flandrin, G. Rilling, P. Goncalves, Empirical mode decomposition as a filter bank. IEEE Signal Process. Lett. 11(2), 112–114 (2004)
A. Goldberger, L. Amaral, L. Glass, J.M. Hausdorff, P. Ivanov, R.G. Mark, J.E. Mietus, G.B. Moody, C.-K. Peng, H.E. Stanley, PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000). (Circulation electronic pages)
R. Hostettler, W. Birk, M.L. Nordenvaad, Extended kalman filter for vehicle tracking using road surface vibration measurements, in Proceedings on IEEE 51st IEEE Conference on Decision and Control, Maui, HI, USA (2012), pp. 5643–5648
N.E. Huang, Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q. Zheng, N.C. Yen, C.C. Tung, H.H. Liu, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. Lond. 454(1971), 903–995 (1998). https://doi.org/10.1098/rspa.1998.0193
J. Jenitta, A. Rajeswari, Denoising of ECG signal based on improved adaptive filter with EMD and EEMD, in 2013 IEEE Conference on Information & Communication Technologies, Thuckalay, Tamil Nadu, India (2013), pp. 957–962. https://doi.org/10.1109/CICT.2013.6558234
M. Kania, M. Fereniec, R. Maniewski, Wavelet denoising for multilead high resolution ECG signals. Meas. Sci. Rev. 7(4), 30–33 (2007)
H. Kaur, R. Ni, ECG signal denoising with Savitzky–Golay, filter and discrete wavelet transform (DWT). Int. J. Eng. Trends Technol. 36(5), 266–269 (2016). https://doi.org/10.14445/22315381/IJETT-V36P249
K. S. Kumar, B. Yazdanpanah, P. R. Kumar, Removal of noise from electrocardiogram using digital FIR and IIR filters with various methods, in International Conference on Communications and Signal Processing (ICCSP), Melmaruvathur, India (2015), pp. 157–162
M. Kumar, R.B. Pachori, U.R. Acharya, Automated diagnosis of myocardial infarction ECG signals using sample entropy in flexible analytic wavelet transform framework. Entropy 19(9), 488 (2017). https://doi.org/10.3390/e19090488
C. Lastre-Domínguez, Y.S. Shmaliy, O. Ibarra-Manzano, J. Munoz-Minjares, L.J. Morales-Mendoza, ECG signal denoising and features extraction using unbiased FIR smoothing. Biomed. Res. Int. (2019). https://doi.org/10.1155/2019/2608547
D. Li, Z. Liang, L.J. Voss, J.W. Sleigh, Analysis of depth of anesthesia with Hilbert–Huang spectral entropy. Clin. Neurophysiol. 119(11), 2465–2475 (2008). https://doi.org/10.1016/j.clinph.2008.08.006
J. Li, G. Deng, W. Wei, H. Wang, Z. Ming, Design of a real-time ECG filter for portable mobile medical systems. IEEE Access 5, 696–704 (2017)
Q. Li, R. Li, K. Ji, W. Dai, Kalman filter and its application, in Proceedings on 8th International Conference on Intelligent Networks and Intelligent Systems, Tianjin, China (2015), pp. 74–77
S. Z. Mahmoodabadi, A. Ahmadian, M.D. Abolhasani, ECG feature extraction using Daubechies wavelets, in Proceeding of the Fifth IASTED International Conference VISUALIZATION, Spain (2005), pp. 343–348
A. Mert, A. Akan, Seizure onset detection based on frequency domain metric of empirical mode decomposition. Signal Image Video Process. 12(8), 1489–1496 (2018). https://doi.org/10.1007/s11760-018-1304-y
J. Mielniczuk, P. Wojdyłło, Estimation of Hurst exponent revisited. Comput. Stat. Data Anal. 51(9), 4510–4525 (2007). https://doi.org/10.1016/j.csda.2006.07.033
G.B. Moody, W.E. Muldrow, R.G. Mark, A noise stress test for arrhythmia detectors. Comput. Cardiol. 11, 381–384 (1984)
I. Nouira, A. Ben Abdallah, M.H. Bedoui, M. Dogui, A robust R peak detection algorithm using wavelet transform for heart rate variability studies. Int. J. Electr. Eng. Inform. 5(3), 270–284 (2013)
M.A. Ouali, K. Chafaa, M. Ghanai, L. E Moreno, D.B. Rojas, ECG denoising using extended Kalman filter, in 2013 International Conference on Computer Applications Technology, Sousse, Tunisia (2013). https://doi.org/10.1109/ICCAT.2013.6521994
P. Phukpattaranont, Improvement of signal to noise ratio (SNR) in ECG signals based on dual-band continuous wavelet transform, in Signal and Information Processing Association Annual Summit and Conference, Asia-Pacific, Siem Reap, Cambodia (2014), pp. 1–4
S. Poungponsri, X. Hua Yu, An adaptive filtering approach for electrocardiogram (ECG) signal noise reduction using neural networks. Neurocomputing 117, 206–213 (2013). https://doi.org/10.1016/j.neucom.2013.02.010
M.Z.U. Rahman, R.A. Shaik, D.V. Rama Koti Reddy, Efficient sign based normalized adaptive filtering techniques for cancelation of artifacts in ECG signals: application to wireless biotelemetry. Signal Process. 91(2), 225–239 (2011). https://doi.org/10.1016/j.sigpro.2010.07.002
B. Richhariya, M. Tanveer, EEG signal classification using universum support vector machine. Expert Syst. Appl. 106, 169–182 (2008). https://doi.org/10.1016/j.eswa.2018.03.053
D. Salmond, Target tracking: introduction and Kalman tracking filters, in Proceedings on IEE Workshop Target Tracking: Algorithms and Applications (Ref. No. 2001/174), Enschede, Netherlands (2001), pp. 1–16
M. Shahbakhti, A novel DWT method for ECG noise elimination. IEEJ Trans. Electr. Electron. Eng. 10(3), 353–355 (2015). https://doi.org/10.1002/tee.22093
K. Takeuchi, N. Collier, Bio-medical entity extraction using support vector machines. Artif. Intell. Med. 33(2), 125–137 (2005). https://doi.org/10.1016/j.artmed.2004.07.019
M.M. Tantawi, K. Revett, A.B. Salem, M.F.A. Tolba, wavelet feature extraction method for electrocardiogram (ECG)-based biometric recognition. Signal Image Video Process. 9(6), 1271–1280 (2015). https://doi.org/10.1007/s11760-013-0568-5
A.K. Verma, I. Saini, B.S. Saini, Alexander fractional differential window filter for ECG denoising. Australas. Phys. Eng. Sci. Med. 41(2), 519–539 (2018). https://doi.org/10.1007/s13246-018-0642-y
R. Vullings, B. de Vries, J.W.M. Bergmans, An adaptive Kalman filter for ECG signal enhancement. IEEE Trans. Biomed. Eng. 58(4), 1094–1103 (2010). https://doi.org/10.1109/TBME.2010.2099229
G. Wahyudi, M.I. Fanany, W. Jatmiko, A. Murni Arymurthy, SVM kernels accuracy and generalization capability on Apnea detection from ECG, in International Conference 2010 Information Systems (2010), pp. 187–191. https://doi.org/10.13140/RG.2.1.4573.8325
L. Wang, J. Li, R. Zhu, L. Xu, Y. He, R. Zhang, S. Rao, A novel stepwise support vector machine (SVM) method based on optimal feature combination for predicting miRNA precursors. Afr. J. Biotechnol. 10(74), 16720–16731 (2011). https://doi.org/10.5897/AJB11.2273
Z. Wang, Adaptive Fourier decomposition based ECG denoising. Comput. Biol. Med. 77(Supplement C), 195–205 (2016). https://doi.org/10.1016/j.compbiomed.2016.08.013
H. Xiao, Z. Xiao, N. Zhang, Removal of baseline wander from ECG signal based on a statistical weighted moving average filter. Front. Inf. Technol. Electron. Eng. 12(5), 397–403 (2011). https://doi.org/10.1631/jzus.C1010311
P. Xiong, H. Wang, M. Liu, S. Zhou, Z. Hou, X. Liu, ECG signal enhancement based on improved denoising auto-encoder. Eng. Appl. Artif. Intell. 52, 194–202 (2016). https://doi.org/10.1016/j.engappai.2016.02.015
E.A. Zanaty, Support Vector Machines (SVMs) versus Multilayer Perception (MLP) in data classification. Egypt. Inform. J. 13(3), 177–183 (2012). https://doi.org/10.1016/j.eij.2012.08.002
Y. Zhang, C. Liu, S. Wei, C. Wei, F. Liu, ECG quality assessment based on a kernel support vector machine and genetic algorithm with a feature matrix. Front. Inf. Technol. Electron. Eng. 15(7), 564–573 (2014). https://doi.org/10.1631/jzus.C1300264
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors report no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Assali, I., Nouira, I., Abidi, A. et al. Intelligent ECG Signal Filtering Method Based on SVM Algorithm. Circuits Syst Signal Process 42, 1773–1791 (2023). https://doi.org/10.1007/s00034-022-02196-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-022-02196-z