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

A feature extraction method and corresponding monitoring system for multi-lead ECG signals

A feature extraction and electrical signal technology, applied in the fields of application, diagnostic recording/measurement, medical science, etc., can solve the problems of low accuracy rate of automatic classification of ECG signals, short duration of ECG signals, and difficult capture, etc., to improve automatic The effect of classification accuracy and enhanced feature expression ability

Active Publication Date: 2022-02-11
ZHENGZHOU UNIV +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the existing electrocardiographic signal feature extraction method is not easy to capture the abnormal changes of short duration and small amplitude in the electrocardiographic signal, which leads to the problem that the automatic classification accuracy of the electrocardiographic signal is low. Feature extraction method and corresponding monitoring system for multi-lead ECG signals

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
  • A feature extraction method and corresponding monitoring system for multi-lead ECG signals
  • A feature extraction method and corresponding monitoring system for multi-lead ECG signals
  • A feature extraction method and corresponding monitoring system for multi-lead ECG signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] A feature extraction method for multi-lead ECG signals, such as figure 1 and 2 shown, including the following steps:

[0062] Step 1: Obtain a single-lead ECG signal {X(t), t=1,...,N} among the multi-lead ECG signals, and perform j-scale MODWPT decomposition on the single-lead ECG signal, get the 2 of the jth layer j The largest discrete wavelet packet coefficient matrix A corresponding to nodes; where, the jth layer of MODWPT decomposition contains 2 j nodes, and each node corresponds to N wavelet packet coefficients, and t represents the corresponding index value of the wavelet packet coefficients. In this embodiment, the value of the decomposition scale j is 3.

[0063] Formula (1) is the obtained single-lead ECG signal at scale j, which contains 2 j Nodes correspond to the largest discrete wavelet packet coefficient matrix A with the same time resolution as the single-lead ECG signal.

[0064]

[0065] in, Denotes 2 at level j j The value of the tth wave...

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 feature extraction method and a corresponding monitoring system for multi-lead electrocardiographic signals, and relates to the technical field of electrocardiographic signal analysis. (MODWPT) decomposes to get the 2 of the jth layer j The largest discrete wavelet packet coefficient matrix of nodes; calculate the energy of the wavelet packet coefficients in each node of the jth layer and the total energy of all nodes at this scale, and normalize the energy of the wavelet coefficients of each node to obtain each wavelet packet coefficient Calculate the energy entropy value of each node after the energy probability distribution of each node; fuse the energy entropy values ​​of all nodes in the jth layer to form an energy entropy feature matrix; calculate and fuse the energy entropy feature matrices corresponding to all other single-lead ECG signals. The monitoring system corresponding to the method includes a signal acquisition device and a signal monitoring device. The invention can capture abnormal changes with short duration and small amplitude in the electrocardiographic signal, and accurately identify the normal state and abnormal state of the electrocardiographic signal.

Description

technical field [0001] The invention relates to the technical field of electrocardiographic signal analysis, in particular to a feature extraction method for multi-lead electrocardiographic signals and a corresponding monitoring system. Background technique [0002] Electrocardiographic signal (electrocardiosignal) is the electrical signal synthesized by the action potential generated by cardiomyocytes during the regular contraction and relaxation of the heart, and is a comprehensive reflection of the electrical activity of the heart on the body surface. In the process of collecting ECG signals, it can be seen that its dynamic changes have the characteristics of short duration, easy to be disturbed and indistinct features. The automatic classification technology of ECG mainly depends on its feature extraction method. Various features such as time domain features, wavelet features, and entropy features have been used to extract the features of ECG signals. By improving the fe...

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 Patents(China)
IPC IPC(8): A61B5/318A61B5/00A61B5/366
Inventor 师丽韩闯王治忠牛晓可钱龙龙李泓毅
Owner ZHENGZHOU UNIV
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