Automatic Auscultation by using Visual Dot Pattern

Auscultation, listening to sounds coming from human organs, is a primary routine for screening and diagnosing many pathological conditions of the heart. Heart sounds-based methods of diagnosis are designed to explore and investigate the relationships between heart sounds and heart disease using digital signal processing technologies. Most of the conventional methods for analysing heart sound signals are based on observing the amplitude differences in the time or frequency domain.This paper describes a Visual dot pattern (VDP) method, which visualizes sound signals in a diagrammatic representation. Experiments are carried out to evaluate the proposed system for heart sound analysis under various normal and abnormal conditions. Principal Component Analysis (PCA) based on eigenspace system is used as classifier for image patterns obtained. Heart Sound signalspatterns are successfully recognized as normal and abnormal Heart Sound such as Aortic Stenosis (AS), Mitral Stenosis (MS), Aortic Regurgitation (AR) and Mitral Regurgitation (MR).