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

Electrocardiosignal graph classification method based on deep learning

A technology of electrocardiogram and deep learning, applied in neural learning methods, medical science, instruments, etc., can solve problems such as poor classification and poor generalization ability of automatic classification algorithms, and achieve high classification performance

Inactive Publication Date: 2021-03-16
HARBIN UNIV OF SCI & TECH
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem of poor classification of some categories by the traditional single convolutional neural network or single loop neural network and to solve the automatic Due to the poor generalization ability of classification algorithms, a classification method based on deep learning for ECG images is proposed.

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
  • Electrocardiosignal graph classification method based on deep learning
  • Electrocardiosignal graph classification method based on deep learning
  • Electrocardiosignal graph classification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0018] A kind of classification method based on the electrocardiogram of deep learning of the present embodiment, such as Figure 5 As shown, the method is realized through the following steps:

[0019] Step 1, preprocessing the image data of the collected electrocardiogram; wherein the preprocessing includes the steps of wavelet denoising of the image data of the electrocardiogram and data enhancement of the image data of the electrocardiogram;

[0020] Step 2. Design a convolutional neural network;

[0021] Step 3, using the designed convolutional neural network to classify the electrocardiogram.

specific Embodiment approach 2

[0023] The difference from the first embodiment is that in this embodiment, a deep learning-based classification method for electrocardiograms, in the first step, the wavelet denoising process of the image data of the electrocardiograms is specifically:

[0024] The wavelet method is used for noise reduction, and the wavelet coefficients are analyzed, the coefficients with smaller absolute values ​​are set to 0, and the coefficients with larger absolute values ​​are retained or shrunk, and then the processed wavelet coefficients are reconstructed to obtain the denoising signal. Depend on figure 1 It can be seen that the wavelet transform method eliminates the noise relatively well while retaining the useful signal.

specific Embodiment approach 3

[0026] The difference from the second specific embodiment is that in this embodiment, a deep learning-based classification method of ECG diagrams, in the first step, the step of data enhancement of the image data of ECG diagrams is specifically as follows:

[0027] Because the amount of sample data contained in the MIT-BIH arrhythmia data set itself used in the present invention is not large enough, in order to ensure that all sample data can be fully utilized, the data equalization method is not to under-sample a large amount of data samples, but to The oversampling operation is used for small data volume samples. First, the cardiac beat frequency of small data volume samples is expanded to any frequency between 60-120bpm, and then the original ECG data is sampled according to the randomly expanded frequency using the second-order interpolation algorithm. , the specific calculation process is as follows:

[0028]

[0029]

[0030]

[0031] Among them, L i The length...

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 an electrocardiosignal graph classification method based on deep learning, and belongs to the field of image recognition. A traditional single convolutional neural network or single recurrent neural network has the problem of poor classification in part of categories, and has the problem of poor generalization ability of an automatic classification algorithm caused by different representations under the same disease due to individual differences such as heartbeat intensity, heart rate and the like. The invention discloses an electrocardiosignal graph classification method based on deep learning. The method comprises the following steps: preprocessing acquired image data of the electrocardiosignal graph, wherein the preprocessing includes wavelet denoising of the image data of the electrocardiosignal graph and data enhancement of the image data of the electrocardiosignal graph; designing a convolutional neural network, and classifying the electrocardiosignal graph by utilizing the designed convolutional neural network. The electrocardiosignal recognition and classification effect can be remarkably improved.

Description

technical field [0001] The invention relates to a classification method of electrocardiograms based on deep learning. Background technique [0002] The traditional single convolutional neural network or single recurrent neural network has the problem of poor classification on some categories. Moreover, due to individual differences such as heartbeat intensity and heart rate, different representations of the same disease lead to poor generalization ability of automatic classification algorithms. Contents of the invention [0003] The purpose of the present invention is to solve the problem of poor classification of some categories by traditional single convolutional neural network or single loop neural network and to solve the automatic In order to solve the problem of poor generalization ability of classification algorithms, a classification method based on deep learning for electrocardiograms is proposed. [0004] A kind of classification method based on the electrocard...

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): G06K9/62G06N3/04G06N3/08A61B5/346
CPCG06N3/084A61B5/7264A61B5/7267G06N3/044G06N3/045G06F18/24G06F18/214
Inventor 杨明极韩子昂刘畅
Owner HARBIN UNIV OF SCI & TECH
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