Bayesian denoising framework of phonocardiogram based on a new dynamical model

In this paper, we introduce a model-based Bayesian denoising framework for phonocardiogram (PCG) signals. The denoising framework is ounded on a new dynamical model for PCG, which is capable of generating realistic synthetic PCG signals. The introduced dynamical model is ased on PCG morphology and is inspired by electrocardiogram (ECG) dynamical model proposed by McSharry et al. and can represent various orphologies of normal PCG signals. The extended Kalman smoother (EKS) is the Bayesian filter that is used in this study. In order to facilitate he adaptation of the denoising framework to each input PCG signal, the parameters are selected automatically from the input signal itself. This pproach is evaluated on several PCGs recorded on healthy subjects, while artificial white Gaussian noise is added to each signal, and the SNR and orphology of the outputs of the proposed denoising approach are compared with the outputs of the wavelet denoising (WD) method. The results f the EKS demonstrate better performance than WD over a wide range of PCG SNRs. The new PCG dynamical model can also be employed to evelop other model-based processing frameworks such as heart sound segmentation and compression.