Related Experiment Video
Updated: May 7, 2026
08:51
Data Acquisition and Analysis In Brainstem Evoked Response Audiometry In Mice
Published on: May 10, 2019
Multi-level basis selection of wavelet packet decomposition tree for heart sound classification.
Fatemeh Safara1, Shyamala Doraisamy, Azreen Azman
1Department of Multimedia, Faculty of Computer Science and Information Technology, University Putra Malaysia, 43400 UPM Serdang, Selangor Darul Ehsan, Malaysia; Department of Computer Engineering, Islamic Azad University, Islamshahr Branch, Tehran, Iran.
Computers in Biology and Medicine
|September 17, 2013
Summary
This study introduces multi-level basis selection (MLBS) for wavelet packet transform to enhance signal feature extraction. MLBS accurately classifies heart sounds, showing promise for frequency-limited signals.
Area of Science:
- Biomedical Signal Processing
- Machine Learning in Healthcare
- Digital Signal Analysis
Background:
- Wavelet packet transform (WPT) offers a flexible framework for signal decomposition.
- Effective feature extraction from WPT requires optimal selection of decomposition bases.
- Existing methods may not efficiently isolate the most informative components for specific signal types.
Purpose of the Study:
- To propose a novel multi-level basis selection (MLBS) method for WPT.
- To improve feature extraction by preserving informative bases and removing redundant ones.
- To evaluate the efficacy of MLBS in classifying cardiac auscultation signals.
Main Methods:
- Developed a multi-level basis selection (MLBS) algorithm for WPT.
- Implemented three exclusion criteria: frequency range, noise frequency, and energy threshold.
- Applied MLBS to extract features from heart sound signals for classification.
Main Results:
- MLBS successfully preserved the most informative bases within the WPT decomposition tree.
- Achieved a high classification accuracy of 97.56% for four cardiac conditions.
- Demonstrated effectiveness in classifying normal heart sound, aortic stenosis, mitral regurgitation, and aortic regurgitation.
Conclusions:
- Multi-level basis selection (MLBS) is an effective strategy for optimizing WPT feature extraction.
- The proposed MLBS method shows significant promise for analyzing signals with limited frequency ranges, such as heart sounds.
- MLBS offers a robust approach for improving diagnostic accuracy in cardiovascular signal analysis.
Keywords:
ARASBBSDFTDWTECGENGETFeature extractionHeart murmurLDBMLBSMRMulti-level basis selectionPCGPhonocardiographic signal (PCG)RBFRENGRelative energySLBSSNRSTFTSVMSupport vector machineWPTWavelet packet transformaortic regurgitationaortic stenosisbest basis selectiondiscrete wavelet transformelectrocardiographic signalenergyenergy thresholdlocal discriminant basismitral regurgitationmulti-level basis selectionphonocardiographic signalradial basis functionrelative energyshort time fourier transformsignal -to-noise ratiosingle-level basis selectionsupport vector machinewavelet packet transformRelated Concept Videos
01:15Heart Sounds
Heart sounds are generated by the turbulence in blood flow due to the closing of heart valves. These sounds are best perceived slightly away from the valves, where the blood flow disseminates the sound.
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V) valves at the...
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V) valves at the...
01:30Classification of Signals
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
01:30Heart Failure IV: Classification and Diagnostic Evaluation
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...