A Novel Feature Extraction Method for Heart Sounds Classification
Yücel Koçyiğit · IWBBIO · 2014
The experimental results showed that the proposed method efficient- ly classifies heart sounds. Heart sound analysis is a b asic method for heart ex- amination, w hich m ay s uggest t he pr esence of a c ardiac pa thology a nd a lso provide diagnostic information. In this study, a novel feature extraction method based on Independent Component Analysis is applied to classify nine different heart sound categories. The extracted features are subjected to classification by Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) using 5 Cross V alidation a nd b y A rtificial N eural N etwork. T he ex perimental r esults showed that the proposed method efficiently classifies heart sounds.