Adaptive Filtering Strategy to Remove Noise from ECG Signals Using Wavelet Transform and Deep Learning

Electrocardiogram (ECG) is a method to measure the electrical activity of the heart which is performed by placing electrodes on the surface of the body. Physicians use observation tools to detect and diagnose heart diseases, the same is performed on ECG signals by cardiologists. In particular, heart diseases are recognized by examining the graphic representation of heart signals which is known as ECG. The ECG signals are accompanied by noise due to external sources or other physiological processes in the human body.

In this applied research, an adaptive filter based on wavelet transform and deep neural network was proposed to reduce the noise. The proposed method was a combination of wavelet transform, adaptive learning, and nonlinear mapping of deep neural networks. Deep neural network was used with an adaptive filter to reduce more noise in the ECG signal.

Signal-to-Noise ratio (SNR) was used as a criterion to evaluate the quality of the proposed method to remove noise. In fact, the objective of this research was to increase this ratio which indicates higher efficiency of the method based on wavelet transform and deep learning.

The results of the simulation showed that the proposed method improved the removal of noise from the ECG signal about 9.56% compared to existing methods. The reason is that the coefficients extracted from adaptive filter were optimized using deep neural network so that it provided a low-noise waveform.