A5055855684- Phonocardiography and Auscultation Techniques
- Music and Audio Processing
- Machine Fault Diagnosis Techniques
- Blind Source Separation Techniques
- Cardiac Valve Diseases and Treatments
- Fault Detection and Control Systems
- Speech and Audio Processing
- Medical Image Segmentation Techniques
- Currency Recognition and Detection
- ECG Monitoring and Analysis
Hunan Institute of Science and Technology
2024
Nanyang Institute of Technology
2014-2021
Yamaguchi University
2010-2014
Xihua University
2010
To utilize heart sound features that may vary according to their suitability for segmentation, automatic adaptive feature extraction combined with the Mahalanobis distance classification criterion is proposed construct an innovative, sound-based system diagnosing diseases. The innovation of this primarily reflected in segmentation and first complex ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CS</i> <sub...
In this paper, the Mahalanobis distance classification criterion combined with principal component analysis (PCA)-based heart sound features generation is proposed for diagnosing three-type ventricular septal defects (VSDs): small VSDs (SVSDs), moderate (MVSDs), and large (LVSDs). The three stages corresponding to diagnostic system implementation are summarized as follows. first stage, collected via a stethoscope filtered using wavelet decomposition. second time-domain [t <sub...
In this study, a simple system based on PCA-based heart sound feature extraction is proposed for discriminating ventricular septal defects (VSDs), which are generally divided into three types: small VSDs (SVSDs), moderate (MVSDs) and large (LVSDs). The stages corresponding to the discrimination implementation summarized as follows. stage 1, collected by stethoscope preprocessed using wavelet decomposition (WD). 2, time domain features [T12, T11] first extracted from envelope Et, signal Xt...
A fixed split in the second heart sound ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</i> <sub xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) indicates an aortic septal defect (ASD). This work aims at shortcomings of using time interval xmlns:xlink="http://www.w3.org/1999/xlink">T</i> xmlns:xlink="http://www.w3.org/1999/xlink"><i>A</i><sub>2</sub>→<i>P</i><sub>2</sub></sub> between sounds produced by valve closure...
This paper is concerned with a novel proposal to determinate classification boundaries both in time and frequency domains based on the support vector machines (SVM) technique for diagnosis of ventricular septal defect (VSD). Firstly, two heart sound characteristic waveforms are extracted from time-domain frequency-domain. Four feature parameters domains, [T11, T12] [FG, FW], obtained crossed points at selected threshold values. Secondly, algorithm determine surrounding proposed aid SVM...
Abstract Background: As an efficient method, heart sounds ( HSs ) analysis by classifying the features extracted from four-stage sequence consisting of first sound S 1 ), second 2 duration to and , has been widely used diagnose disease evaluate functions. However, feature is difficult be with high accuracy due four stages segmented low accuracy; fixed classifiers achieved training old samples cannot better fit new ones because they are not adjusted incremental features. Thus, a novel intelligent...
A novel intelligent diagnostic system is proposed to diagnose heart sounds (HSs). The innovations of this are primarily reflected in the automatic segmentation and extraction first complex sound (CS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> ) second xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ); secondary envelope-based features γ - , xmlns:xlink="http://www.w3.org/1999/xlink">3</sub> from CS ; adjustable classifier models...