Skip to Main content Skip to Navigation
Conference papers

The Empirical Mode Decomposition and the SVD for Abnormal Heart Sound Signals detection and Time-Frequency Analysis.

Abstract : Phonocardiogram signals (PCGs) generated by the flow of blood in the heart hold the physiological characteristics of the heart. Sometimes, it carries pathological characteristics in the cardiac diseases where a lot of information is reflected in the heart murmurs. Analyzing some pathological Heart Sound Signals (HSs) in order to detect the murmurs is an important and useful problem. Then, extracted some features may be used to characterize some cardiac disease. In this paper, we explore the aptitude of the Empirical Mode Decomposition (EMD) in conjunction with the Singular Value Decomposition (SVD). The EMD allows decomposing a multicomponent signal into a set of monocomponent signals, called Intrinsic Mode Functions (IMFs). The method follows with the calculation of the Singular Entropy (SE) used to discriminate between the pathological cases in consideration. Also, relevant features distinguishing different cases of heart diseases are obtained by spectrogram results. Applications of four real abnormal cases such as: Early Aortic stenosis (EAS), Late Aortic Stenosis (LAS), Mitral Regurgitation (MR), and the Opening Snap (OS) cases show that the successfully to detect pathological murmur.
Document type :
Conference papers
Complete list of metadatas

https://hal-centralesupelec.archives-ouvertes.fr/hal-01266589
Contributor : Myriam Baverel <>
Submitted on : Wednesday, February 3, 2016 - 9:11:31 AM
Last modification on : Wednesday, September 16, 2020 - 4:51:24 PM

Identifiers

Citation

Daoud Boutana, Messaoud Benidir, N. Nayad. The Empirical Mode Decomposition and the SVD for Abnormal Heart Sound Signals detection and Time-Frequency Analysis.. The IET Conference on Intelligent Signal Processing (ISP 2015), Dec 2015, Londres, United Kingdom. ⟨10.1049/cp.2015.1780⟩. ⟨hal-01266589⟩

Share

Metrics

Record views

191