Characterization of $S_1$ and $S_2$ Heart Sounds Using Stacked Autoencoder and Convolutional Neural Network

This paper proposes a new technique for the identification of fundamental heart sounds (HSs), namely, <inline-formula> <tex-math notation="LaTeX">$S_{1}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$S_{2}$ </tex-math></inline-formula> from the cardiac cycle, the first and foremost step in the automated HSs analysis for the detection of pathological events, without incorporating time-interval informations between <inline-formula> <tex-math notation="LaTeX">$S_{1}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$S_{2}$ </tex-math></inline-formula> or electrocardiogram signal as reference. The motive of this paper is to demonstrate that the reliable <inline-formula> <tex-math notation="LaTeX">$S_{1}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$S_{2}$ </tex-math></inline-formula> classification performances based on the combinatory feature (CF) derived from higher order moments and cepstral-based domain can still be achieved, under the circumstances where the timing interval information might not be easily understood due to cardiac abnormalities. Using deep neural networks approach, a stacked autoencoder (SAE) based on the CF is proposed for the classification of fundamental HSs. Experiments are conducted on both publicly available and recorded HSs signals for the validation of the proposed method. The SAE using the proposed CF achieves better classification results in recognizing <inline-formula> <tex-math notation="LaTeX">$S_{1}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$S_{2}$ </tex-math></inline-formula> in comparison to well-known classifiers such as deep belief neural network, support vector machine, Naive Bayes, linear discriminant analysis, and boosting ensemble. The proposed method shows higher classification rate in terms of accuracy, sensitivity, and specificity by considering CF, which uses Mel-frequency cepstral coefficients and its derivative features. A second approach for addressing the problem of <inline-formula> <tex-math notation="LaTeX">$S_{1}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$S_{2}$ </tex-math></inline-formula> identifications is carried out by employing 1-D convolutional neural network that uses the signals directly to learn the relevant features by its own for the recognition.