ECG Denoising by Sparse Wavelet Shrinkage

Noise removal of electrocardiogram (ECG) signal has always been a subject of great study. A novel sparse wavelet shrinkage method is proposed based on maximum likelihood estimation for ECG signal corrupted with Gaussian noise. The method utilizes the prior information on the probability density of the data. The features and shrinkage parameters are estimated directly from the data. Noisy ECG signal collected from clinic recording is processed using the method. The results show that on contrast with traditional methods, the novel wavelet shrinkage method can achieve the optimal denoising of the ECG signal.