Heart sound feature representation using extended modified bdistribution

Heart sound analysis has gathered increasing attention over the past few years as the maturity of processing algorithms start to produce reliable and promising results. This work highlights the advantages of recently developed time frequency method which is Modified B-Distribution (MBD) and Extended Modified B-Distribution (EMBD). The approach was tested against real subjects with normal and abnormal type of heart sound and murmurs. The result shows that the EMBD is able to reveal more valuable murmurs signal as compared to MBD which provides the vital information in detecting the presence of heart disease