Identification of ${S}_{\text{1}}$ and ${S}_{\text{2}}$ Heart Sounds Using Spectral and Convex Hull Features

Abstract

A new set of morphological characteristics of Phonocardiogram (PCG) signal is presented for recognition of first ( ${S}_{{1}}$ ) and second ( ${S}_{{2}}$ ) heart sounds (HSs). Initially, variational mode decomposition on PCG signal generates a set of amplitude and frequency modulated narrow band-limited components (NBCs) and Hilbert transformation of these NBCs comprehends its complex plane analytic signal representation (ASR). Instantaneous spectral attributes encompassing amplitude modulation bandwidths and convex hull area measure from the ASRs are concatenated to form the feature set. Experimental results on both publicly available and experimentally recorded HSs signals outperform the existing state-of-the-art. Also, the proposed technique does not require any timing information between ${S}_{{1}}$ and ${S}_{{2}}$ and electrocardiogram (ECG) signal reference and is highly robust to noisy real-world PCGs as shown by noise analysis.