Perfoma Discrete Wavelet Transform dalam Denoising Sinyal EKG Berdasarkan Evaluasi Signal-to-Noise Rasio

Febriyanti Panjaitan; Rizki Amalia

doi:10.33633/tc.v21i4.6961

Authors

Febriyanti Panjaitan Universitas Bina Darma http://orcid.org/0000-0002-4905-5876
Rizki Amalia Universitas Bina Darma

DOI:

https://doi.org/10.33633/tc.v21i4.6961

Keywords:

Denoising, Elektrodiagram, DWT, SNR, Performance

Abstract

Denoising adalah cara dalam menghilangkan noise yang ada pada sinyal elektrodiagram, sehingga gelombang yang ada pada elektrodiagram dapat dianalisis dengan menggunakan mesin untuk mendapatkan prediksi penyakit jantung yang diderita. Beberapa penelitian yang telah menganalisis sinyal elektrodiagram mengusulkan metode denoising dengan menggunakan Discrete Wavelet Transform, karena metode ini memberikan solusi kualitas yang lebih baik dibandingkan dengan metode denoising lainnya. Penelitian ini akan bertujuan melakukan denoising dengan menggunakan metode Discrete Wavelet Transform serta membandingkan performa dari wavelet family yang terdapat pada metode tersebut dengan persamaan evaluasi Signal-to-Noise Rasio. Data yang digunakan adalah data pasien yang memiliki diagnosis Venticular Tachycardia yang diambil dari data MITB. Penelitian memberikan hasil dan gambaran hasil denoising untuk setiap wavelet family yang ada pada Discrete Wavelet Transform. Berdasarkan hasil evaluasi Signal-to-Noise Rasio bahwa sym6 dan db6 memberikan perfoma yang lebih baik dibandingkan dengan wavelet family yang lainnya, karena kedua wavelet ini memiliki nilai yang lebih tinggi.

References

M. Aqil, A. Jbari, and A. Bourouhou, “ECG Signal Denoising by Discrete Wavelet Transform.,” Int. J. Online Eng., vol. 13, no. 9, 2017.

G. T. Ramadhani, A. Adiwijaya, and D. Q. Utama, “Klasifikasi Penyakit Aritmia Melalui Sinyal Elektrokardiogram (ekg) Menggunakan Metode Local Features Dan Support Vector Machine,” eProceedings Eng., vol. 5, no. 1, 2018.

M. Risnasari, “Penekanan Noise Pada Sinyal EKG Menggunakan Transformasi Wavelet,” J. Ilm. Edutic Pendidik. dan Inform., vol. 1, no. 1, 2014.

S. Kaplan Berkaya, A. K. Uysal, E. Sora Gunal, S. Ergin, S. Gunal, and M. B. Gulmezoglu, “A survey on ECG analysis,” Biomed. Signal Process. Control, vol. 43, pp. 216–235, 2018.

O. Heriana and A. M. Al Misbah, “Comparison of wavelet family performances in ECG signal denoising,” J. Elektron. dan Telekomun., vol. 17, no. 1, pp. 1–6, 2017.

S. L. Joshi, R. A. Vatti, and R. V Tornekar, “A survey on ECG signal denoising techniques,” in 2013 International Conference on Communication Systems and Network Technologies, 2013, pp. 60–64.

I. Mohapatra, P. Pattnaik, and M. N. Mohanty, Cardiac Failure Detection Using Neural Network Model with Dual-Tree Complex Wavelet Transform, vol. 846. Springer Singapore, 2019.

N. A. Polytechnic, “Detection of Shockable Ventricular Arrhythmia using Optimal Orthogonal Wavelet Filters Detection of Shockable Ventricular Arrhythmia using Optimal Orthogonal Wavelet Filters,” no. January, 2019.

J. D. Roberts et al., “Electrocardiographic intervals associated with incident atrial fibrillation: Dissecting the QT interval,” Hear. Rhythm, vol. 14, no. 5, pp. 654–660, 2017.

S. B. Anuja, U. N. K, and S. T. Sukanya, “ECG Signals Classification using Statistical and Wavelet Features,” Int. J. Recent Technol. Eng., vol. 8, no. 5, pp. 1497–1504, 2020.

D. Zhang et al., “An ECG signal de-noising approach based on wavelet energy and sub-band smoothing filter,” Appl. Sci., vol. 9, no. 22, 2019.

S. Mandala, Y. N. Fuadah, M. Arzaki, and F. E. Pambudi, “Performance analysis of wavelet-based denoising techniques for ECG signal,” in 2017 5th International Conference on Information and Communication Technology (ICoIC7), 2017, pp. 1–6.

W. Jenkal, R. Latif, A. Toumanari, A. Dliou, O. El B’charri, and F. M. R. Maoulainine, “An efficient algorithm of ECG signal denoising using the adaptive dual threshold filter and the discrete wavelet transform,” Biocybern. Biomed. Eng., vol. 36, no. 3, pp. 499–508, 2016.

G. Kaushik, H. P. Sinha, and L. Dewan, “BIOMEDICAL SIGNALS ANALYSIS BY DWT SIGNAL DENOISING WITH NEURAL NETWORKS.,” J. Theor. Appl. Inf. Technol., vol. 62, no. 1, 2014.

H. Serhal, N. Abdallah, J.-M. Marion, P. Chauvet, M. Oueidat, and A. Humeau-Heurtier, “Overview on prediction, detection, and classification of atrial fibrillation using wavelets and AI on ECG,” Comput. Biol. Med., p. 105168, 2022.

“MIT-BIH Arrhythmia Database Directory (Introduction).” [Online]. Available: https://archive.physionet.org/physiobank/database/html/mitdbdir/intro.htm#annotations. [Accessed: 27-Jun-2022].

“MIT-BIH Arrhythmia Database v1.0.0.” [Online]. Available: https://physionet.org/content/mitdb/1.0.0/. [Accessed: 27-Jun-2022].

A. B. H. Adamou-Mitiche, L. Mitiche, and H. Naimi, “Three levels discrete wavelet transform elliptic estimation for ECG denoising,” in 2016 4th International Conference on Control Engineering & Information Technology (CEIT), 2016, pp. 1–5.

R. Von Borries, P. JH, and H. Nazeran, “Redundant Discrete Wavelet Transform for ECG Signal Processing (< Special Issue> Biosensors: Data Acquisition, Processing and Control),” Int. J. Biomed. Soft Comput. Hum. Sci. Off. J. Biomed. Fuzzy Syst. Assoc., vol. 14, no. 2, pp. 71–81, 2009.

S. Mallat, A wavelet tour of signal processing. Elsevier, 1999.

R. Von Borries, J. H. Pierluissi, and H. Nazeran, “Redundant discrete wavelet transform for ECG signal processing,” Biomed Soft Comput Hum Sci, vol. 14, no. 2, pp. 69–80, 2009.

H.-Y. Lin, S.-Y. Liang, Y.-L. Ho, Y.-H. Lin, and H.-P. Ma, “Discrete-wavelet-transform-based noise removal and feature extraction for ECG signals,” Irbm, vol. 35, no. 6, pp. 351–361, 2014.

R. S. Singh, B. Singh, S. Ramesh, and K. Sunkaria, “Arrhythmia detection based on time – frequency features of heart rate variability and back-propagation neural network,” Iran J. Comput. Sci., vol. 2, no. 4, pp. 245–257, 2019.

M. Systems, S. Sabut, M. Mohanty, and P. K. Biswal, “Machine learning approach to recognize ventricular arrhythmias using VMD based features,” no. April, 2019.

Y. A. Altay and A. S. Kremlev, “Signal-to-Noise Ratio and Mean Square Error Improving Algorithms Based on Newton Filters for Measurement ECG Data Processing,” in 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus), 2021, pp. 1590–1595.

C. Sawant and H. T. Patii, “Wavelet based ECG signal de-noising,” in 2014 First International Conference on Networks & Soft Computing (ICNSC2014), 2014, pp. 20–24.