Heart Sound Classification from Wavelet Decomposed Signal Using Morphological and Statistical Features

Munia, Tamanna T. K.; Tavakolian, Kouhyar; Verma, Ajay; Zakeri, Vahid; Khosrow-Khavar, Farzad; Fazel-Rezai, Reza; Akhbardeh, Alireza

doi:10.22489/cinc.2016.172-318

Cited by 9 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to demonstrate the spectral peaks in the PCG, a sub-frame of a sampled PCG signal is considered. By using Burg's methods AR (12) spectrum is constructed and shown in Fig. valve prolapse (MVP).…”

Section: Burg's Spectrum Based Formant Extractionmentioning

confidence: 99%

“…Apart from the various statistical measures, we consider six operations, namely mean absolute deviation (MAD), 1 st quartile, 3 rd quartile, inter quartile range (IQR), skewness and kurtosis. Considering two formants, these operations provide 12 parameters for each case of the formants (magnitude (F 12 Mag, Stats ), frequency (F 12 Freq, Stats ) and phase (F 12 Pha, Stats )). If we closely observe Fig.…”

Section: E Formation Of the Feature Dictionarymentioning

confidence: 99%

“…Envelope/envelogram based methods were mostly used for both segmentation and classification purposes of the PCG signals. Shannon energy envelogram [11], Shannon envelogram on wavelet decomposed signal [12], Shannon envelogram on S-transformed signal [13], envelogram from Hilbert transformed signal [14], moment waveform envelogram [15], squared energy envelogram [16] etc. are the most commonly used available methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Heart Valve Disorder Detection Based on PDF Modeling of Formant Variation Pattern in PCG Signal

2022

View full text Add to dashboard Cite

Heart valve disorder (HVD) analysis from heart sound is being well known for a long period of time, and use of digital stethoscope gives opportunity to diagnose HVDs from phonocardiographic (PCG) signal. An automated HVD detection technique from PCG signal can play a key role as a firsthand diagnostic tool for the physicians. In this paper, in order to classify different HVDs, we propose to utilize the formant characteristic of the PCG signal, which is an acoustic property of the heart sound. PCG signals exhibit significant variations depending on different types of HVDs and thus conventional time frequency domain features or statistical features are extracted from PCG signal for disease classification. However, direct PCG signals are also used in sequential networks to classify HVDs. Similar to the formant peaks of voiced speech signal, the spectrum corresponding to the PCG signal exhibits distinguishable peaks, especially in the voiced part of the heart sound (lub-dub). Keeping this notable key point in consideration, Burg's autoregressive model is used to find the parametric spectrum of the PCG signal. The first two formants of the PCG signal, that carry the most informative acoustic properties of the heart sound, are estimated from the Burg's spectrum, and are used for feature extraction. The magnitude, frequency and phase of each formant are considered to evaluate these features. Instead of considering a long duration of PCG signal at a time, we consider the overlapping sub-frames, and extract formants from each subframe, which generates a temporal variation of the formants. Finally, we propose a PDF model fitting of the formant variation, and utilize the estimated model parameters along with some statistical features to classify the HVDs. Two famous publicly available PCG datasets are used to demonstrate the performance of the proposed method, that efficiently classify the binary/five classes of heart sounds. The results reveal that the proposed method has the overall accuracy values of 93.46% and 99.28% for the two datasets, which is better in comparison to other previously reported state-of-the-art techniques.

show abstract

Section: Burg's Spectrum Based Formant Extractionmentioning

confidence: 99%

Section: E Formation Of the Feature Dictionarymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Heart Valve Disorder Detection Based on PDF Modeling of Formant Variation Pattern in PCG Signal

2022

View full text Add to dashboard Cite

show abstract

“…During the CinC 2016 conference, most of the participants have used time-frequency features, in particular the wavelet decomposition coefficients and Mel-Cepstral Frequency Coefficients (MFCCs). [5][6][7] Linear predictive coding coefficients have been also used. 7 In terms of classifiers, competitors mostly used Neural Networks, 5,8,9 Support Vector Machines 10,11 and Random Forest techniques.…”

Section: Prior Artmentioning

confidence: 99%

A benchmark of heart sound classification systems based on sparse decompositions

Ibarra-Hernández

Bertin

Alonso-Arévalo

et al. 2018

14th International Symposium on Medical Information Processing and Analysis

View full text Add to dashboard Cite

Background: Nowadays, cardiovascular diseases (CVD) remain the main cause of death worldwide. A heart sound signal or phonocardiogram (PCG) is the most simple, economical and non-invasive tool to detect CVDs. Advances in technology and signal processing allow the design of computer-aided systems for heart illnesses detection from PCG signals. Purpose: The paper proposes a pipeline and benchmark for binary heart sounds classification. The features extraction architecture is focused on the use of Matching Pursuit time-frequency decomposition using Gabor dictionaries and the Linear Predictive Coding method of a residual. We compare seven classifiers with two different approaches: feature averaging and cycle averaging. Methods: We test our proposal on the PhysioNet/CinC challenge 2016 database, which comprises a wide variety of heart sounds recorded from patients with normal and different pathological heart conditions. We conduct a 10-fold stratified cross-validation method to evaluate the performance of different classification algorithms. The feature sets were also tested when using an oversampling method for balancing. Results: The benchmark identified systems showing a satisfying performance in terms of accuracy, sensitivity, and Matthews correlation coefficient. Results can be improved when using feature averaging and an oversampling strategy.

show abstract

“…Numerous automated classi cation methods, such as Arti cial Neural Networks (ANN), Hidden Markov Model (HMM), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Deep Neural Networks (DNN), have been implemented [8], [10], [11]. In [12], the authors utilized a discrete wavelet transform to derive forty-two features. These features were then subjected to testing a support vector machine classi er, employing ve distinct kernel functions.…”

Section: Introductionmentioning

confidence: 99%

Classification of Phonocardiogram Signals Using the Wavelet Scattering Transform and Equilibrium Optimization Approach

Ismael,

Abd,

Homod

2024

Preprint

View full text Add to dashboard Cite

Heartbeat sounds serve as biological signals that aid in the early identification of cardiovascular conditions. Phonocardiograms (PCG), which are recordings of digital heartbeat sounds, are employed for the identification and automated categorization of potential heart ailments. This research presents a technique for categorizing heart sounds by combining WST (Wavelet Scattering Transform) & EO (Equilibrium Optimization). The signal of cardiac sound can be divided into 2 main kinds, abnormal & normal, concerning the signal of PCG. This work analyzes the characteristics of the phonocardiogram signal and subsequently employs machine learning methods to classify these features. During the feature-extracting process, we employed wavelet scattering in conjunction with the equilibrium optimizer method. We utilized the K-Nearest Neighbor (KNN) classifier for the purposes of learning and categorization. The experiments aimed to assess the impact of the optimization technique on the algorithm's performance, demonstrating its effectiveness. The findings revealed that our method achieved an accuracy of 99.5% when applied to the PCG dataset in distinguishing abnormal heart sounds from normal ones, surpassing the performance of all previous methods.

show abstract

Heart Sound Classification from Wavelet Decomposed Signal Using Morphological and Statistical Features

Abstract: Abstract

Cited by 9 publications

References 10 publications

Automated Heart Valve Disorder Detection Based on PDF Modeling of Formant Variation Pattern in PCG Signal

Automated Heart Valve Disorder Detection Based on PDF Modeling of Formant Variation Pattern in PCG Signal

A benchmark of heart sound classification systems based on sparse decompositions

Classification of Phonocardiogram Signals Using the Wavelet Scattering Transform and Equilibrium Optimization Approach

Contact Info

Product

Resources

About