Algorithm for detecting the first and the second heart sounds by spectral tracking

Multistage decision‐based heart sound delineation method for automated analysis of heart sounds and murmurs

“…Heart murmurs are often characterised by the timing (early, mid, or late), intensity, duration, pitch (low, medium, or high), quality (blowing, rumbling, or musical), and configurations of crescendo, decrescendo, crescendo-decrescendo [1][2][3][4][5][6][7][8]. Thus, an automated delineation method for accurate measurements of sound parameters including amplitude, frequency content, duration, systolic, and diastolic intervals, timing, and configuration of murmurs is most important for effective diagnosis of cardiovascular diseases.Many heart sound segmentation (HSS) methods were reported based on the reference electrocardiogram (ECG) and/or carotid pulse (CP) signals [3], empirical mode decomposition (EMD) [4,5], hidden Markov models [7], wavelet transform (WT), and wavelet packet transform [8][9][10], temporal-spectral features [11][12][13][14], homomorphic envelogram, and self-organising probabilistic model [15], Hilbert transform [16,17], support vector machine [18], and artificial neural network [19]. On the basis of the feature extraction approaches, the HSS methods can be categorised into four major groups: (i) ECG and/or CP waveform-based methods, (ii) temporal-spectral feature-based methods, (iii) envelope-based methods, and (iv) hybrid methods.…”

“…On the basis of the feature extraction approaches, the HSS methods can be categorised into four major groups: (i) ECG and/or CP waveform-based methods, (ii) temporal-spectral feature-based methods, (iii) envelope-based methods, and (iv) hybrid methods. In the ECG or/and CP-based methods, segmentation performance depends heavily on the accurate detection of the R-wave and T-wave in ECG signal, and the systolic peak and dicrotic notch in CP waveforms under time-varying ECG and CP morphologies and various types of artefacts and noise [20].In the temporal-spectral-based methods [11][12][13][14], the segmentation task was performed based on the temporal features including, short-term energy, zero-crossing rate, entropy, kurtosis, autocorrelation function, and the spectral features including sub-band energy ratio, spectral flux, spectral centroid, and harmonics are used for …”

“…Many heart sound segmentation (HSS) methods were reported based on the reference electrocardiogram (ECG) and/or carotid pulse (CP) signals [3], empirical mode decomposition (EMD) [4,5], hidden Markov models [7], wavelet transform (WT), and wavelet packet transform [8][9][10], temporal-spectral features [11][12][13][14], homomorphic envelogram, and self-organising probabilistic model [15], Hilbert transform [16,17], support vector machine [18], and artificial neural network [19]. On the basis of the feature extraction approaches, the HSS methods can be categorised into four major groups: (i) ECG and/or CP waveform-based methods, (ii) temporal-spectral feature-based methods, (iii) envelope-based methods, and (iv) hybrid methods.…”

“…In the temporal-spectral-based methods [11][12][13][14], the segmentation task was performed based on the temporal features including, short-term energy, zero-crossing rate, entropy, kurtosis, autocorrelation function, and the spectral features including sub-band energy ratio, spectral flux, spectral centroid, and harmonics are used for…”

“…In the temporal-spectral-based methods [11][12][13][14], the segmentation task was performed based on the temporal features including, short-term energy, zero-crossing rate, entropy, kurtosis, autocorrelation function, and the spectral features including sub-band energy ratio, spectral flux, spectral centroid, and harmonics are used for detecting heart sounds S1 and S2 in the PCG signal. In the envelope-based segmentation methods, one or more feature envelope(s) are extracted by using the following operations in either time-domain or transform domain [11,[14][15][16][17]: absolute, energy, Shannon energy, Shannon entropy, instantaneous amplitude, instantaneous energy, instantaneous frequency, and autocorrelation coefficient.…”