Publication

Abstract : Computer aided diagnosis (CAD) framework gains huge importance in today's medical world for the automatic cardiac disease monitoring. The CAD framework requires preprocessing of acquired phonocardiogram (PCG) signals to extract informative features from it. Denoising is an important preprocessing step for cardiac disease diagnosis. This paper proposes a novel, group sparsity assisted synchrosqueezing approach for improved PCG signal denoising. In the proposed approach, the PCG signals are initially denoised by exploiting the group sparse (GS) property of the heart sound signals. In the second step, the denoised result is improved by utilizing the synchrosqueezing wavelet transform (SSWT) by eliminating the unwanted higher order frequency components using the extracted intrinsic mode type functions. The robustness of the proposed approach is evaluated by using several PCG signal databases. The superior performance compared to other existing models confirms that the proposed approach can be useful for improved PCG denoising tasks in automatic cardiac monitoring systems