|
Análisis Acústico sobre Se ales de Auscultación Digital para la Detección de Soplos Cardíacos.Keywords: Machine Learning , Acoustic Analysis , Pathologic Detection , Cardiac Murmurs and Phonocardiography Abstract: A methodology based on acoustic analysis of digitized phonocardiographic signals (PCG) is presented, oriented to detection of cardiac murmurs originated by valvular pathologies. Initially, a filtration system based on the wavelet transform is developed to reduce the disturbances that usually appear in the acquisition stage, adjusting the sound quality according to the clinical requirements and validated for specialists in semiology. A segmentation algorithm based on the normalized average Shannon energy and wavelet transform isproposed. Features derived from the acoustic analysis are extracted on the segments. Feature effectiveness is evaluated by a support vector machine in cascade-conFigurauration for separating the classes: normal, murmur and other. The used database of phonocardiographic records belongs to the National University of Colombia, having 111 records as follows: 37 records labeled as “normal”, 24 labeled as “murmur” and 50 labeled as “other ” abnormalities. The classification results are obtained with the original signals and when the signals have been filtered. The filtering stage increases the classificationaccuracy to 96% .
|