Abstract:
PCG (phonocardiogram) plays very important role in heart function analysis. It is a weak biological signal with the strong noise . The biomedical signal recordings are so complex and non-stationary that they are also affected by different kinds of noise making their interpretation quite difficult. In this research we propose algorithm to extract heart sound components based on wavelet transform and de-noise technique increase the precision of the detection process. A proposed algorithm include data were analyzed with aim to find a suitable feature subset for automatic classification of heart sound. The signals are evaluated in our experiments on 28 signals . The proposed algorithm reaches high accuracy by compaired with respect to the diagnosis established by the clinicians
