Identification of Human Heart Valves Mechanical Characteristic Locations via Processing of Phonocardiogram Signal

This paper presents a new method for detection,delineation and unsupervised classification of PCG sounds. First, the PCG signal was preprocessed and then for detection and delineation of the PCG genuine sounds incidence locations, two windows were slid on the pre processed PCG signal. In each slid of the analysis window, the value of mid-sample of the first window was replaced by a frequency based feature of the signal excerpted by the window and the value of mid-sample of the second window was replaced by an amplitude based feature of the signal excerpted by the window. Then a final feature was extracted by the combination of these two features. By these calculations peaks representing location of the sounds incidence appears and can be delineated by various methods such as application of a minimum slope forward-backward local search starting from the sound location. The operating characteristics of the proposed method is the average accuracy Acc=98.91% and 93.50% for sound detection and unsupervised classification, respectively.

Keywords:

Valvular Vibration , Phonocardiography , heart sound , Characteristic Locations , Auscultation