Short unsegmented PCG classification based on ensemble classifier

Abstract

: Diseases associated with the heart are one of the main reasons of death worldwide. Hence, early examinationof the heart is important. For analysis of cardiac disorders, a study of heart sounds is a crucial and beneficial approach.Still, automated classification of heart sounds is a challenging task that mainly depends on segmentation of heart soundsand derivation of features using segmented samples. In the literature available for PCG classification provided byPhysioNet/CinC Challenge 2016, most of the research has focused on enhancing the accuracy of the classification modelbased on complicated segmentation processes and has failed to improve the sensitivity. In this paper, we present anautomated heart sound classification by eliminating the segmentation steps using multidomain features, which resultsin enhanced sensitivity. The study is based on homomorphic envelogram, mel frequency cepstral coefficient (MFCC),power spectral density (PSD), and multidomain feature extraction. The extracted features are trained using the 5-foldcross-validation method based on an ensemble boosting algorithm over 100 independent iterations. Our proposed designis evaluated using public datasets published in PhysioNet/Computers in Cardiology Challenge 2016. Accuracy of 92.47%with improved sensitivity of 94.08% and specificity of 91.95% is achieved using our model. The output performanceproves that our proposed model offers superior performance results.