Goda et al. [70] combined DWT, time features, and other features for classification of heart sounds.
In an extension of this work [53], authors employed a number of machine learning algorithms for classification of heart sounds.
Artificial Neural Network (ANN) finds use in classification of heart sounds for its discriminative training ability and easy implementation.
Since the frequency contents of various heart signals are different, the frequency spectra can be exploited for classification of heart beats.
Among other wavelet based contributions, Naseri and Homaeinezhad [61] proposed a framework for classification of heart sounds S1, S2, S3, S4, murmurs, and scuffles.
And the proposed cardiac sound murmurs classification method with autoregressive spectral analysis and multi-SVM classifiers is validated for the classification of heart valvular disorders.
n = 5 for E/e′ ratio reported in the DCM group, since E/e′ ratio measurements were discarded in patients with moderate-to-severe mitral regurgitation AS aortic valve stenosis, DCM dilated cardiomyopathy, BSA body surface area, NYHA New York Heart Association functional classification of heart failure, Hb hemoglobin.
The clinical status of individual IV:13 changed from asymptomatic to NYHA I (classification of heart failure according to the New York Heart Association) during follow-up.
Classification of heart sound is another research area that divides heartbeat sounds in different clusters based on their characteristics [ 1, 4, 5].
According to the classification of heart failure syndromes, acute decompensated heart failure (ADHF) was reported in 55.3%, hypertensive AHF in 4.4%, pulmonary edema in 18.4%, cardiogenic shock in 14.7%, high output failure in 3.3%, and right heart failure in 3.8%.
