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

Heart beat classification method, device, equipment and storage medium based on U-Net network

A classification method and network technology, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as manual extraction of features, achieve accurate diagnosis results, facilitate practical application and promotion, and be widely applicable

Active Publication Date: 2020-04-03
CHENGDUSCEON ELECTRONICS
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the existing heartbeat classification method needs to manually extract features, the purpose of the present invention is to provide a U-Net network-based heartbeat classification method, device, equipment and storage medium

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 beat classification method, device, equipment and storage medium based on U-Net network
  • Heart beat classification method, device, equipment and storage medium based on U-Net network
  • Heart beat classification method, device, equipment and storage medium based on U-Net network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] like Figure 1~3 As shown, the heart beat classification method based on the U-Net network provided in this embodiment may, but is not limited to, include the following steps S101-S102.

[0051] S101. Using the sample ECG signal as the input of the U-Net network model, using the determined cardiac beat classification label of the sample ECG signal as the output of the U-Net network model, and dividing the training sample set and the verification sample set, And after importing the initial optimizer and the initial evaluation index set, adopt the cross-validation method to train and verify the U-Net network model, through the automatic adjustment of the hyperparameters, the automatic configuration of the evaluation index and / or the optimization The automatic selection of device obtains and saves the heartbeat classification model, wherein, the U-Net network of the U-Net network model is sampled to build a one-dimensional convolutional neural network.

[0052] In the ste...

Embodiment 2

[0066] like Figure 4 As shown, the present embodiment provides a hardware device for implementing the U-Net network-based heart beat classification method described in Embodiment 1, including a model training unit and a classification prediction unit; the model training unit is used to convert the sample ECG The signal is used as the input of the U-Net network model, and the determined cardiac beat classification label of the sample ECG signal is used as the output of the U-Net network model, and the training sample set and the verification sample set are divided, and the initial setting of the import After the optimizer and the initial evaluation index, the U-Net network model is trained and verified by the cross-validation method, and through the automatic adjustment of the hyperparameters, the automatic configuration of the evaluation index and / or the automatic selection of the optimizer, the obtained And save the heart beat classification model, wherein, the U-Net network...

Embodiment 3

[0069] like Figure 5 As shown, this embodiment provides a hardware device for implementing the U-Net network-based heartbeat classification method described in Embodiment 1, including a memory and a processor connected by communication, wherein the memory is used to store computer programs and heart beats. The electrical signal data, the processor is used to execute the computer program to implement the steps of the heart beat classification method based on the U-Net network as described in Embodiment 1.

[0070] The working process, working details and technical effects of the aforementioned equipment provided in this embodiment can be referred to Embodiment 1, and will not be repeated here.

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 relates to the technical field of automatic detection of electrocardiogram signals, and discloses heart beat classification method, device, equipment and storage medium based on U-Net network. The heart beat classification method based on the U-Net network provided by the invention is a new method which is capable of realizing automatic classification of heart beats by adopting a machine learning model based on the U-Net network, and specifically comprises the following steps: designing a U-Net network model of one-dimensional convolution neural network; inputting electrocardiogram data into the U-Net network model so as to be subjected to training and cross validation, thereby obtaining a heart beat classification recognition model; and then, performing heart beat classification on electrocardiogram signals to be tested by using the recognition model, thereby obtaining corresponding heart beat classification results. Therefore, many problems of manual feature extractionand traditional machine learning can be relieved, and model input can be carried out without artificial design or electrocardiogram feature extraction so as to achieve accurate diagnostic results; andthus, the heart beat classification method based on the U-Net network can be widely applied to common arrhythmia detection, thereby facilitating practical application and promotion.

Description

technical field [0001] The invention belongs to the technical field of automatic detection of electrocardiographic signals, and in particular relates to a heart beat classification method, device, equipment and storage medium based on a U-Net network. Background technique [0002] The incidence of arrhythmias increases with the aging of the global population, the most common types of heart beats are: sinus normal beat, atrial premature beat (APB), ventricular premature beat (PVC), left bundle branch block (LBBB) and right bundle branch block (RBBB), all but the first are morphological pulsatile elements that characterize and constitute complex arrhythmias. [0003] The current medical routine for arrhythmia screening is electrocardiography, but some arrhythmias are not easy to detect, and are clinically asymptomatic, and even require long-term monitoring to be discovered. To provide automatic monitoring of human ECG signals for a long time) need to paste electrode sheets, w...

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): A61B5/04A61B5/0402A61B5/00
CPCA61B5/7267A61B5/316A61B5/318
Inventor 杨珊王春丽唐勋李斌
Owner CHENGDUSCEON ELECTRONICS
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