HYBRID EVENT: You can participate in person at Tokyo, Japan or Virtually from your home or work.

International Heart Congress

May 24-25 | Hybrid Event

May 24 -25, 2023 | Tokyo, Japan
Heart Congress 2023

ECG denoising based on WATV and convex fused lasso denoising with non-convex regularization

Abdallah Rezgui, Speaker at Heart Congress
Ecole Nationale Superieure d’Ingenieurs de Tunis (ENSIT), Tunisia
Title : ECG denoising based on WATV and convex fused lasso denoising with non-convex regularization

Abstract:

In this paper, we propose a novel approach of Electrocardiogram (ECG) Denoising based on Wavelet/Total Variation (WATV) and Convex fused lasso Denoising with non-convex regularization. This approach consists at first step of applying the Discrete Wavelet Transform (DWT) to the noisy ECG signal for obtaining a noisy approximation coefficient, ?cAb?_1 and a noisy details coefficient, ?cDb?_1. The latter is denoised by soft thresholding and we obtain a first denoised details coefficient, ?cDd?_1. The second step of this approach consists of applying the DWT to ?cAb?_1 in order to obtain a second noisy approximation coefficient, ?cAb?_2 and a second noisy details coefficient, ?cDb?_2. The latter is denoised by Convex fused lasso denoising with non-convex regularization and we obtain a second denoised details coefficient, ?cDd?_2. The noisy approximation coefficient, ?cAb?_2, is denoised by WATV based denoising technique and we obtain a  denoised approximation coefficient, ?cAd?_2. The inverse of DWT is then applied to ?cDd?_2 and ?cAd?_2 in order to obtain a denoised approximation coefficient, ?cAd?_1. The inverse of DWT is again applied to ?cDd?_1 and ?cAd?_1 for obtaining finally a denoised ECG signal. The performance of this proposed approach is proved by the computation of the Signal to Noise Ratio (SNR), the Peak SNR (PSNR), the Mean Square Error (MSE), the Mean Absolute Error (MAE), and the Cross-Correlation (CC).

Audience Takeaway:

  • The audience will be able to use what they learn by simulating our proposed ECG denoising approach via Matlab/Simulink.
  • This research work can help the audience in their job by providing them an overview on many research works dealing with ECG Denoising including our approach proposed in this work.
  • Yes of course, this research work can be used by other faculties for expanding their researches or teaching and this thanks to theoretical background on ECG Denoising.
  • No, it is just a simulation under Matlab/Simulink of our new proposed ECG Denoising technique.
  • Yes of course, it provide new information to assist in a design problem by giving a new approach of ECG Denoising based on WATV and Convex fused lasso denoising with non-convex regularization.

Biography:

Abdallah Rezgui is actually preparing his PhD thesis at Ecole Nationale Superieure d’Ingenieurs de Tunis (ENSIT), Tunis, Tunisia. He has obtained his Bachelor degree in Electrical Engineering from Faculty of Sciences of Tunis in 2020. He has obtained his Master degree in Electrical Engineering from Faculty of Sciences of Tunis in 2022.

Watsapp