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

Electrocardiosignal noise reduction method based on interpretable deep neural network

A deep neural network and electrocardiographic signal technology, applied in the field of electrocardiographic signal processing, can solve the problems of neural network lack of interpretability and robustness, and achieve the effect of improving interpretability and noise reduction ability

Active Publication Date: 2022-07-22
SHANDONG ARTIFICIAL INTELLIGENCE INST +1
View PDF21 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It not only solves the robustness problem of the traditional model, but also solves the problem of the lack of interpretation of the neural network

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 noise reduction method based on interpretable deep neural network
  • Electrocardiosignal noise reduction method based on interpretable deep neural network
  • Electrocardiosignal noise reduction method based on interpretable deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] In step a), ten clean signals of 103, 105, 111, 116, 122, 205, 213, 219, 223, and 230 in the MIT-BIH database are selected, and BW and EM in the noise pressure database in the MIT-BIH database are selected. , MA as noise data, by inputting the signal-to-noise ratio formula, the noise data with a signal-to-noise ratio of 1.25dB and 5dB is injected into the clean signal to obtain a noisy signal.

Embodiment 2

[0068] The training set samples divided in step b) are 480 segments, each segment has a length of 512, and the divided test set samples are 120 segments, each segment has a length of 512.

Embodiment 3

[0070] Step d) includes the following steps:

[0071] d-1) The first processing unit is sequentially composed of a convolutional layer with a channel number of 64, a convolution kernel size of 1×3, and a LeakyReLU activation function. After the training set is input to the first processing unit, the output channel number is 64-dimensional. characteristic signal T 1 ;

[0072] d-2) The second processing unit is sequentially composed of a convolutional layer with a channel number of 64, a convolution kernel size of 1×5, and a LeakyReLU activation function. After the training set is input to the second processing unit, the output channel number is 64-dimensional. characteristic signal T 2 ;

[0073] d-3) The third processing unit is sequentially composed of a convolutional layer with 64 channels, a convolution kernel size of 1×7, and a LeakyReLU activation function. After the training set is input to the third processing unit, the output channel number is 64-dimensional. char...

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 noise reduction method based on an interpretable deep neural network, and the method comprises the steps: building an electrocardiosignal model through a sparse representation algorithm, and converting an optimization problem into optimization of two sub-problems through a semi-secondary splitting algorithm. Then, a neural network is built in the two sub-problems, and an optimal solution is sought through end-to-end training of electrocardiosignal noise data and clean data in the built neural network. By designing the electrocardiosignal noise reduction network, the interpretability of the neural network is improved, and meanwhile, the noise reduction capacity of electrocardiosignals is also improved. An attractive bridge is established between a traditional sparse representation noise reduction algorithm and a deep neural network noise reduction model. In this way, the interpretability of the neural network is improved, and the precision and robustness of a traditional sparse representation noise reduction algorithm are improved.

Description

technical field [0001] The invention relates to the technical field of electrocardiographic signal processing, in particular to an electrocardiographic signal noise reduction method based on an interpretable deep neural network. Background technique [0002] Cardiovascular disease seriously endangers human health. However, cardiovascular diseases are diagnosed by collecting ECG signals of patients, and abnormal conditions of different bands of the ECG signals are expressed as different heart diseases of the patient. In the process of collecting ECG signals, it is inevitable that different noises will be introduced to distort the ECG signals. Therefore, in order to obtain a clean signal, the noise reduction of the ECG signal has become an indispensable step. [0003] At present, there are empirical mode decomposition, wavelet filtering, Bayesian filtering, sparse representation and neural network noise reduction methods that have been studied a lot recently. For the tradit...

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): G06K9/00G06N3/04G06N3/08A61B5/318A61B5/00
CPCG06N3/08A61B5/318A61B5/7203A61B5/7235G06N3/045G06F2218/00G06F2218/04G06F2218/08
Inventor 刘瑞霞侯彦荣舒明雷陈长芳单珂
Owner SHANDONG ARTIFICIAL INTELLIGENCE INST
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