Heart sound analysis using EMD algorithm

A new unsupervised and low complexity method for detection of S1 and S2 components of heart sound without the ECG reference is proposed. A heart sound segmentation algorithm, which separates the heart sound signal into four parts: the first heart sound, the systolic period, the second heart sound, and the diastolic period has been developed. The algorithm uses empirical mode decomposition (EMD) to produce intensity envelopes of main heart sounds in time domain. The performance of the proposed algorithm has been evaluated using 14000 cardiac periods from 100 digital phonocardiographic recordings including normal and abnormal heart sounds. The algorithm has shown over 90 percent correct ratio.