12-lead ECG signal classification method based on combined two-dimensional features

A signal classification, two-dimensional feature technology, applied in instruments, computing, character and pattern recognition, etc., can solve the problems of low classification performance, inability to effectively use 12-lead data, etc., to improve classification accuracy, improve classification performance, The effect of mitigating data imbalance

Pending Publication Date: 2022-07-05
SHANDONG UNIV OF SCI & TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most current ECG signal classification methods use single-lead data, and these methods cannot effectively use 12-lead data that contains more information, resulting in low classification performance

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
  • 12-lead ECG signal classification method based on combined two-dimensional features
  • 12-lead ECG signal classification method based on combined two-dimensional features
  • 12-lead ECG signal classification method based on combined two-dimensional features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] In step a), the 12-lead database is the INCART database.

Embodiment 2

[0074] In step b), use db8 wavelet to Signal i Perform 8-scale decomposition, by Calculate the data Coe after wavelet transformation, where α is a scale factor greater than 0, τ is the translation amount of the wavelet function, is the db8 wavelet, is the Signal at time t i value of .

Embodiment 3

[0076] In step d), the pywt.waverec() function in python is used to reconstruct the ECG data after removing the wavelet coefficients containing noise.

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

According to the 12-lead ECG signal classification method based on the combined two-dimensional features, 12-lead ECG data can be effectively used, and data differences of different ECG leads can be compared very efficiently through splicing combination, so that richer and more comprehensive ECG feature information is obtained, and the ECG classification precision is effectively improved. The problem of data imbalance can be effectively relieved by using the weighted loss function, and the classification performance of the method can be improved.

Description

technical field [0001] The invention relates to the field of ECG signal classification, in particular to a 12-lead ECG signal classification method based on combined two-dimensional features. Background technique [0002] Electrocardiogram (ECG) is widely used as a non-invasive, simple, efficient and low-cost heart state detection tool. However, most of the current ECG signal classification methods use single-lead data, and these methods cannot effectively use 12-lead data containing more information, resulting in low classification performance. SUMMARY OF THE INVENTION [0003] In order to overcome the deficiencies of the above technologies, the present invention provides a method for acquiring more abundant and comprehensive ECG feature information. [0004] The technical scheme adopted by the present invention to overcome its technical problems is: [0005] A 12-lead ECG signal classification method based on combined two-dimensional features, comprising the following ...

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
IPC IPC(8): G06K9/00
CPCG06F2218/06G06F2218/12
Inventor 舒明雷解洪富刘辉朱亮刘瑞霞
Owner SHANDONG UNIV OF SCI & TECH
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