Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Heart sound signal classification identification method

A signal classification and recognition method technology, applied in signal pattern recognition, character and pattern recognition, instruments, etc., can solve the problems of detection errors, peak point omission, inconvenience, etc., to improve processing efficiency, reduce processing capacity, The effect of improving accuracy

Active Publication Date: 2018-08-31
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This technology improves the quality of analyzing and extracting biomedial signals from body tissues like blood vessels or muscles by optimizing their properties while reducing its size without requiring complicated steps such as sectioning them into smaller parts beforehand.

Problems solved by technology

This patented technical problem addressed in this patents relates to improving methods for identifying and distinguishing between different types of heart activity (cardiac) based on their physical properties like shape size, movement pattern, etc., without requiring manual intervention during diagnostic procedures due to its lack of specificity and reliance upon patient perception.

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 classification identification method
  • Heart sound signal classification identification method
  • Heart sound signal classification identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] Below in conjunction with accompanying drawing, the present invention is described in further detail:

[0056] like figure 1 As shown, the present invention mainly includes the following steps

[0057] 1. Preprocess the heart sound signal x(i)

[0058] In order to avoid the difference in the collection environment and collection standard of the heart sound data, first reduce the sampling frequency of the heart sound signal x(i) to 2000HZ, and then use a Butterworth low-pass filter with a phase of zero and a frequency band of 0-900HZ for noise reduction processing, followed by normalizing the denoised heart sound signal, then:

[0059]

[0060] 2. Perform discrete wavelet decomposition on the preprocessed heart sound signal to obtain the normalized average fragrant energy envelope

[0061]For the normalized heart sound signal, the heart sound wavelet is used for 4-layer wavelet decomposition. Due to the morphological similarity of the heart sound signal, the approx...

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 discloses a heart sound signal classification identification method comprising the following steps: carrying out discrete wavelet decomposition for preprocessed heart sound signals, thusobtaining a detail wavelet coefficient and an approximation wavelet coefficient of different frequency bands; solving a normalization average fragrant energy envelope and an autocorrelation functionof the detail wavelet coefficient and the approximation wavelet coefficient in sequence, thus obtaining autocorrelation characteristics of the detail wavelet coefficient envelope and autocorrelation characteristics of the approximation wavelet coefficient envelope; using a local linear embedding algorithm to respectively carry out non-linear characteristic dimension reduction for the detail autocorrelation characteristics and approximation autocorrelation characteristics, and fusing the dimension reduced detail characteristics and the approximation characteristics so as to obtain fusion characteristics; finally, using the fusion characteristics as support vector machine inputs for classification identification. The method can prevent segmented process of the heart sound signals, thus improving the heart sound characteristic extraction accuracy, and providing active effects for pathology heart sound analysis and feature extraction.

Description

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

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
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com