Recognition method of electrocardiosignal based on DWNN framework

An electrocardiographic signal and identification method technology, applied in the field of electrocardiographic signal classification and recognition, and intelligent classification of electrocardiographic signals, can solve the problem of not realizing the tight coupling between wavelet and subsequent classifiers, etc.

Active Publication Date: 2019-12-27
XIAN UNIV OF POSTS & TELECOMM
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above existing technologies all process the feature maps extracted by wavelet transform differently, and then send them to the classifier for learning, and do not realize the tight coupling between wavelet and subsequent classifiers

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
  • Recognition method of electrocardiosignal based on DWNN framework
  • Recognition method of electrocardiosignal based on DWNN framework
  • Recognition method of electrocardiosignal based on DWNN framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described in detail below in conjunction with the examples, which are explanations of the present invention rather than limitations.

[0038] see Figure 1-Figure 3 , Figure 5 , the recognition method of the ECG signal based on DWNN framework that the present invention provides, comprises the following operations:

[0039] 1) Construct a DWNN framework model including a deep feature construction module, a fully connected layer and an output layer, wherein the deep feature extraction module includes n sub-modules composed of wavelet layers and pooling layers, and ECG signals alternately enter wavelet layers and pooling layers The wavelet layer extracts the deep data features in the ECG signal through wavelet decomposition and random weighted reconstruction, and the pooling layer performs pooling and dimensionality reduction on the extracted deep data features, and obtains the deep features of the wavelet structure after alternate p...

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 a recognition method of an electrocardiosignal based on a DWNN framework. An electrocardiogram enters a wavelet layer as original data, the wavelet layer is reconstructed through wavelet decomposition and random weighting, characteristics of deep-layer data in the electrocardiogram are extracted, a pooling layer reduces the dimension of the extracted data characteristics through pooling operation, a full connection layer synthesizes the data characteristics after dimensionality reduction, and an output layer uses a softmax function to output classification results. Among 800 tested electrocardiosignals, 794 electrocardiosignals are predicted correctly and 6 electrocardiosignals are predicted incorrectly by the recognition method, and the prediction accuracy of the recognition method is 99.25%; and the result shows that the recognition method has more obvious classification results and recognition results.

Description

technical field [0001] The invention belongs to the technical field of medical devices, relates to the intelligent classification of electrocardiographic signals, in particular to a classification and identification method of electrocardiographic signals based on a DWNN framework. Background technique [0002] With the rapid development of artificial intelligence, image classification plays an important role in pattern recognition and machine learning. How to use computers to automatically extract image features and automatically classify images has developed into one of the important research topics in the fields of artificial intelligence and computer vision. Image classification is one of the many applications of machine learning in business, medicine, technology, research, finance, and more. Machine learning is an important direction in the field of artificial intelligence. With the in-depth research of neural network algorithms in machine learning, the network algorith...

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): A61B5/0476A61B5/00
CPCA61B5/7264A61B5/7225A61B5/7203A61B5/369
Inventor 包志强邢瑜王宇霆张燕
Owner XIAN UNIV OF POSTS & TELECOMM
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