Abstract:

Cardiac auscultation that is a still widely used technique to diagnose heart murmurs induced by heart disorders. Taking into account that this method is quite subjective and time consuming, the enhancement of diagnosis techniques would contribute significantly to clinical auscultation. Development of computer-aided auscultative diagnosis systems, which provide more objective and reliable results would be beneficial to reduce the classification errors for the cardiac disorder categories. The presented study uses a combination of Mel–frequency cepstral coefficient (MFCC) and Hidden Markov Model (HMM. Classification experiments were conducted on the 84 heart sound data made up of 6 different types of heart sound. From this, average correct classification rate of 98.8% was achieved when the HMM has 5 states and frame size is 25ms.

Keywords: