Heart sound signal characteristic automatic extraction method

A technology for automatic extraction of signal characteristics, applied in medical science, diagnosis, auscultation instruments, etc., can solve problems such as the inability to automatically obtain the characteristic values ​​of the heart sound signal, the envelope is not smooth, and the inability to accurately locate the diastolic and systolic phase of the heart sound signal, etc.

Inactive Publication Date: 2016-06-22
CHONGQING UNIV
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The segmentation and positioning of the heart sound signal by the ECG signal is based on the one-to-one correspondence between the starting points of the Q, R, S, and T waves of the ECG signal and the heart sound signal. The premise is the electrical signal, and at the same time, the automatic acquisition of the characteristic value of the heart sound signal cannot be realized, and its analysis also needs to be manually determined by experienced personnel based on the reference signal
The most commonly used segmentation method in modern times is to use the signal envelope method to segment and locate the signal. Without using the reference signal, the automatic segmentation of the heart sound signal can be realized. Therefore, the algorithm has high requirements and takes a long time. Currently, extraction Most of the algorithms of the signal envelope have the disadvantages that the envelope is not smooth and the original information is lost too much, and the biggest difficulty at present is that the automatic acquisition of the characteristic value of the heart sound signal cannot be realized, especially for the signal containing noise and large interference The accuracy rate is low, and it cannot accurately locate the diastolic and systolic phases of the heart sound signal

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Heart sound signal characteristic automatic extraction method
  • Heart sound signal characteristic automatic extraction method
  • Heart sound signal characteristic automatic extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] The concrete steps of described step c) are:

[0080] c1) for the signal envelope E T (m) After windowing and framing processing, intercept the smooth signal envelope of n cycles as the processing signal envelope; set the threshold line Level=0.01 to intercept the processing signal envelope, and process the signal envelope in n cycles The method of segmenting i periodic signals is as follows:

[0081] c2) Threshold line Level=0.01 has 4 intersection points with the ith cycle signal of the processed signal envelope, and on the horizontal axis, these 4 intersection points are named as the first heart sound of the i-th cycle from left to right The left envelope segmentation point, the right envelope segmentation point of the first heart sound in the i-th cycle, the left envelope segmentation point of the second heart sound in the i-th cycle, the right envelope segmentation point of the second heart sound in the i-th cycle Segment point; on the horizontal axis, save the c...

Embodiment 2

[0092] Step c4) described in embodiment 1 also includes the following steps:

[0093] c5) Get the preprocessed signal X T (k) The time period signal whose abscissa range is the same as the processing signal envelope abscissa range is the processing signal;

[0094] c6) Calculate the short-term energy signal and short-term zero-crossing rate signal of the processed signal, and then set the threshold M H ,which is:

[0095] M H = ∫ 0 M X T ( k ) d k ;

[0096] Threshold M H Intercept the short-term energy signal, and process the i-th period signal in n periods of the short-term energy signal and the short-term zero-crossing rate signal as follows:

[0097] c7) Threshold M H There are 4 intersection points with the i-th cycle signal of the short-term energy signal....

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a heart sound signal characteristic automatic extraction method comprising the following steps: preprocessing a heart sound signal, and using a viola integration waveform method to extract a signal envelope; segmenting the signal envelope, and positioning so as to obtain a first heart sound segment zone and a second heart sound segment zone; calculating a first heart sound segment zone first heart sound characteristic constant and a second heart sound segment zone second heart sound characteristic constant; extracting heart sound signal characteristics. The heart sound signal characteristic automatic extraction method is simple in calculation, fast in speed, can accurately position a heart sound signal diastole stage and contraction stage, can effectively extract heart sound signal characteristic envelope, can reserve original information on the heart sound signal, and is very suitable for analyzing and processing heart sound signal containing noises and interferences.

Description

technical field [0001] The invention relates to the technical field of analysis and processing of heart sound signals, in particular to an automatic feature extraction method of heart sound signals. Background technique [0002] Heart sound is a weak vibration signal transmitted to the chest wall through the surrounding tissue due to the mechanical vibration caused by myocardial contraction and relaxation, opening and closing of the heart valve, and blood flow impacting the ventricular wall and aorta during the cardiac cycle. The heart sound signal contains a lot of information about the heart's physiology and pathology. When the cardiovascular disease has not yet developed enough to produce clinical and pathological changes, the murmurs and distortions in the heart sound are useful for the diagnosis of valvular heart disease and some congenital heart diseases. Significance. [0003] The usual way to detect heart sounds is through heart sound auscultation. Doctors or profes...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): A61B7/00
CPCA61B7/00
Inventor 郭兴明蒋鸿郑伊能
Owner CHONGQING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap