Heart Rate Estimation from Phonocardiogram Signals Using Non-negative Matrix Factorization

Abstract

Electrocardiogram (ECG) is classically considered for heart rate (HR) estimation. However in certain conditions, its use may be difficult and alternative techniques, such as phonocardiograhpy (PCG), are investigated. For PCG signals, in most studies, the challenge is to detect and annotate the heart sounds S 1 and S 2 , which may become quasi-impossible in case of noise. In this paper, we present a novel approach of HR estimation from PCG signals based on non-negative matrix factorization (NMF), applied to the spectrogram of PCG, considered as a source-filter model. Compared to state of the art methods, specific considerations based on the signal properties have been included to ensure the reliability of the decomposition. HR estimations obtained from noise-free and noisy real PCG signals are evaluated by comparison to HR estimation from synchronous ECG.

Fetal heart rate estimation by non-invasive single abdominal electrocardiography in real clinical conditions

“…This temporal modeling of ECG signal is also valid for fetal ECG. Note that a similar type of excitation-filter modeling has also been investigated [22,23] for phonocardiographic (PCG) signals, that share the same temporal properties with ECG.…”

A Robust and Real-Time Capable Envelope-Based Algorithm for Heart Sound Classification: Validation under Different Physiological Conditions

“…In the future, the envelope curves of the HT and STFT will be combined in order to increase the accuracy of the classification, since both envelope curves contain different information. Moreover, the heart rate could be estimated with the non-negative matrix factorization (NMF) out of the spectrogram, as suggested by [23]. Therefore, the algorithm with the STFT approach could be improved.…”

“…In the literature, the autocorrelation (ACF) is well-established for heart rate estimation out of PCG signals [11,13,20,22]. In 2019, Dia et al proposed a method for extracting the heart rate from noisy PCG signals by using the non-negative matrix factorization (NMF) [23]. They applied the NMF on the spectrogram of a PCG in order to estimate the heart rate.…”

Fetal heart rate estimation from a single phonocardiogram signal using non-negative matrix factorization

“…Indeed, the NMF is a matrix decomposition algorithm that allows to factorize the spectrogram as a product of matrices of lower rank [18], [19]. Applying the NMF on the spectrogram of our sourcefilter model leads to [20], [21] X W (e) H (e) W (ϕ) H (ϕ) ,…”

“…W (ϕ) allows to estimate the spectral envelop of the fetal PCG and the matrix H (ϕ) contains its temporal evolution. These matrices, except W (e) which is fixed, are iteratively updated thanks to our NMFbased algorithm whose details are given in [21].…”