Scholarlink

Electrocardiogram ( \(ECG\) ) signals serve an important role in identifying heart problems, but they are usually distorted by noise, preventing accurate interpretation. This work provides a novel method for denoising \(ECG\) signals using a hybrid methodology that combines deep learning and signal processing techniques. Our method entails decomposing noisy \(ECG\) signals at diverse \(SNR\) values, training a Convolutional Neural Network ( \(CNN\) ) model for learning the mapping from Discrete Wavelet Transform ( \(DWT\) ) approximation coefficient of a noisy signal to that of the corresponding clean signal at each value of Signal to Noise Ratio (SNR), and then applying a Total Variation Denoising ( \(TVD\) ) transform to further refine the denoised results. In this paper, are compared the standalone \(CNN\) -based denoising, the \(TVD\) technique, and our suggested approach. Experimental results from benchmark ECG datasets show that our proposed method outperforms the standalone \(CNN\) and \(TVD\) methods in terms of denoising efficacy. Our technique preserves important \(ECG\) features while efficiently reducing noise aberrations, demonstrating its potential to improve diagnostic accuracy and patient care outcomes in clinical settings.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel Approach of Electrocardiogram Denoising Based on Deep Learning CNN and TVD

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Abdallah Rezgui,
  • Brahim Nasraoui,
  • Mourad Talbi

摘要

Electrocardiogram ( \(ECG\) ) signals serve an important role in identifying heart problems, but they are usually distorted by noise, preventing accurate interpretation. This work provides a novel method for denoising \(ECG\) signals using a hybrid methodology that combines deep learning and signal processing techniques. Our method entails decomposing noisy \(ECG\) signals at diverse \(SNR\) values, training a Convolutional Neural Network ( \(CNN\) ) model for learning the mapping from Discrete Wavelet Transform ( \(DWT\) ) approximation coefficient of a noisy signal to that of the corresponding clean signal at each value of Signal to Noise Ratio (SNR), and then applying a Total Variation Denoising ( \(TVD\) ) transform to further refine the denoised results. In this paper, are compared the standalone \(CNN\) -based denoising, the \(TVD\) technique, and our suggested approach. Experimental results from benchmark ECG datasets show that our proposed method outperforms the standalone \(CNN\) and \(TVD\) methods in terms of denoising efficacy. Our technique preserves important \(ECG\) features while efficiently reducing noise aberrations, demonstrating its potential to improve diagnostic accuracy and patient care outcomes in clinical settings.