Analyzing the Phonocardiogram of ASD-Patient Based on Independent Component Analysis

About 7%o to 11%o of infant born with congenital heart defects (CHD) each year in China. It has made a serious mischance by CHD to our society and the families which suffered from CHD. Atrial septal defect (ASD) is the most incident among CHD cases. It is highly necessary to make pre-diagnosis by digital signal processing. Heart sounds provide physiological and pathological information on the structural integrity and function of the heart. The phonocardiogram (PCG) is a graphic representation of the heart sounds. Independent component analysis (ICA) is a novel method developed in recent years. In this study, the phonocardiogram (PCG) was separated into four components by applying ICA. Then interested characters were extracted based on the result of ICA. The result showed it could successfully separate the ASD-patient´s PCG from normal one based on the characters