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

ECG noise recognition model training and ECG noise detection method and device

A technology for identifying models and training methods, applied in the field of data processing, can solve problems such as wasting time and prone to misjudgment, and achieve the effect of easy high-frequency noise parameters and accurate high-frequency noise parameters

Inactive Publication Date: 2021-11-02
SCI RES TRAINING CENT FOR CHINESE ASTRONAUTS +1
View PDF21 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the problem in the prior art of judging whether the ECG test result is affected by noise through the doctor’s experience. Thereby providing a method and device for ECG noise recognition model training and ECG noise detection

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
  • ECG noise recognition model training and ECG noise detection method and device
  • ECG noise recognition model training and ECG noise detection method and device
  • ECG noise recognition model training and ECG noise detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] An embodiment of the present invention provides a method for training an electrocardiographic noise recognition model, such as figure 1 shown, including the following steps:

[0047] Step S1: Obtain the ECG record data as the training data of the ECG noise recognition model. The ECG record data includes clean segment data without noise and noise segment data including noise. In the embodiment of the present invention, MIT-BIH heart rate is selected The data in the anomaly database is used as training data. The database has rich types of heart beats and is highly representative. The database includes noise annotations. The noise-related annotations are classified as clean and noise, and the two-channel ECG is independently annotated. . When selecting an ECG segment, assuming that the time length of a noise label is t, then select the pure area with a time length t before and after the noise label, and the total length of the recorded data is 3t; but if the time length o...

Embodiment 2

[0099] An embodiment of the present invention provides a method for detecting electrocardiographic noise, such as Figure 7 shown, including the following steps:

[0100] Step S401: Obtain the ECG record data to be detected.

[0101] Step S402: Calculate the electrocardiographic noise parameters of the ECG record data to be detected, and construct the noise feature vector according to the electrocardiographic noise parameters. For details, refer to the relevant description of step S2 in the first embodiment above;

[0102] Step S403: Input the noise feature vector into the electrocardiographic noise recognition model, detect the electrocardiographic record data to be detected, and generate the detection result. The above-mentioned electric noise recognition model is trained by the electrocardiographic noise recognition model training method provided in the above-mentioned embodiment 1. out.

[0103] Through the electrocardiographic noise detection method provided by the embo...

Embodiment 3

[0105] An embodiment of the present invention provides an electrocardiographic noise recognition model training device, such as Figure 8 shown, including:

[0106] The training data acquisition module 1 is used to obtain ECG record data as the training data of the ECG noise recognition model, and the ECG record data includes clean segment data without noise and noise segment data including noise. For details, refer to Relevant description of step S1 in the first embodiment above.

[0107] The noise feature vector construction module 2 is used to calculate the electrocardiographic noise parameters of the training data, and construct the noise feature vector according to the electrocardiographic noise parameters. For details, refer to the relevant description of step S2 in the first embodiment above.

[0108] The electrocardiographic noise recognition model training module 3 is configured to input the noise feature vector into the neural network model for training to obtain th...

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 electrocardiographic noise identification model training and an electrocardiographic noise detection method and device. The electrocardiographic noise identification model training method includes: acquiring electrocardiographic record data as the training data of the electrocardiographic noise identification model, and the electrocardiographic record data includes Clean segment data without noise and noisy segment data containing noise; calculate the ECG noise parameters of the training data; construct the noise feature vector according to the ECG noise parameters; input the noise feature vector into the neural network model for training, and obtain the ECG noise recognition Model. The ECG noise recognition model trained by this method can analyze whether there is noise in each heartbeat more quickly and accurately, and avoid misjudging the low signal-to-noise ratio caused by noise as arrhythmia.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to an electrocardiographic noise identification model training and an electrocardiographic noise detection method and device. Background technique [0002] The ECG signal is an important way to detect arrhythmia, but the ECG signal is easily affected by myoelectric interference, motion artifacts, baseline drift, power frequency common-mode interference, etc. When the ECG signal is interfered by noise, the signal-to-noise ratio decreases. A heart beat with a low signal-to-noise ratio is easily misjudged as an arrhythmia, which brings unnecessary troubles to patients and medical staff. At present, most of the ECG test results are directly submitted to the doctor for analysis. The doctor needs to judge whether the ECG test result is affected by noise based on his own experience, and then extract information about the patient's physical condition through the ECG test result. It...

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): A61B5/318A61B5/366A61B5/352A61B5/00
CPCA61B5/7203A61B5/7267A61B5/7225A61B5/725A61B5/318A61B5/366
Inventor 李延军唐晓英许志
Owner SCI RES TRAINING CENT FOR CHINESE ASTRONAUTS
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