An efficient thresholding technique for segmentation of Phonocardiographic Signals

Segmentation and exact timing information of PCG(Phonocardiographic) Signals and its components S1, Systolic period, S2 and Diastolic period in order with time of great importance for accurate diagnosis. In this work, we propose a novel algorithm for the segmentation of Phonocardiographic Signals into its constituent components having both normal and abnormal pathological conditions. The algorithm introduces an adaptive thresholding technique not only to segment but also to estimate the time duration of different cardiac events. Experimental testing was performed on 950 cycles taken from 13 normal, 27 abnormal and 18 fetal cases. The obtained results show 100.00% accuracy in normal, 95.95% accuracy in abnormal signals and 96.7% accuracy in fetal leading to overall 97% accuracy.