Cardiac disorders are critical and must be diagnosed in the early stage using routine\nauscultation examination with high precision. Cardiac auscultation is a technique to analyze and\nlisten to heart sound using electronic stethoscope, an electronic stethoscope is a device which provides\nthe digital recording of the heart sound called phonocardiogram (PCG). This PCG signal carries\nuseful information about the functionality and status of the heart and hence several signal processing\nand machine learning technique can be applied to study and diagnose heart disorders. Based on\nPCG signal, the heart sound signal can be classified to two main categories i.e., normal and abnormal\ncategories. We have created database of 5 categories of heart sound signal (PCG signals) from various\nsources which contains one normal and 4 are abnormal categories. This study proposes an improved,\nautomatic classification algorithm for cardiac disorder by heart sound signal. We extract features\nfrom phonocardiogram signal and then process those features using machine learning techniques\nfor classification. In features extraction, we have used Mel Frequency Cepstral Coefficient (MFCCs)\nand Discrete Wavelets Transform (DWT) features from the heart sound signal, and for learning and\nclassification we have used support vector machine (SVM), deep neural network (DNN) and centroid\ndisplacement based k nearest neighbor. To improve the results and classification accuracy, we have\ncombined MFCCs and DWT features for training and classification using SVM and DWT. From our\nexperiments it has been clear that results can be greatly improved when Mel Frequency Cepstral\nCoefficient and DiscreteWavelets Transform features are fused together and used for classification\nvia support vector machine, deep neural network and k-neareast neighbor(KNN). The methodology\ndiscussed in this paper can be used to diagnose heart disorders in patients up to 97% accuracy.\nThe code and dataset can be accessed at â??https://github.com/yaseen21khan/Classification-of-Heart-\nSound-Signal-Using-Multiple-Features-/blob/master/README.mdâ?.
Loading....