Electrocardio recognition method with ultralow data volume

A recognition method and data volume technology, applied in the field of signal recognition, can solve the problems of uncertainty, difficult hardware design of random projection matrix, unfavorable random projection matrix application, etc., and achieve the effect of high accuracy, small amount of data, and high precision

Inactive Publication Date: 2018-04-24
SICHUAN UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the hardware design of random projection matrix is ​​difficult and has the disadvantage of uncertainty, which is not conducive to the application of random projection matrix

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
  • Electrocardio recognition method with ultralow data volume
  • Electrocardio recognition method with ultralow data volume
  • Electrocardio recognition method with ultralow data volume

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Below in conjunction with specific embodiment the present invention is described in further detail:

[0019] 1. Chebyshev chaos matrix construction

[0020] The Chebyshev chaotic observation matrix is ​​a common one-dimensional mapping method, which is a system combined with trigonometric functions, and its definition form is as formula (1):

[0021] (1)

[0022] initial value , from which the chaos matrix can be obtained by iteration

[0023] 1. Chaotic projection matrix feature extraction

[0024] Compressed sensing theory points out that as long as the signal is compressible or sparse in a certain transform domain, then a high-dimensional signal can be projected onto a low-dimensional space with an observation matrix that is irrelevant to the transform basis. If the given signal is , we consider an observation system that requires m linear observations. This process can be described mathematically as

[0025] (2)

[0026] in, for order matrix, . ...

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 electrocardio recognition method with the ultralow data volume. The method is used for electrocardio signal feature extraction and belongs to the field of signal recognition. The method is characterized by comprising the following steps of (1) performing feature extraction on electrocardio signals by using a compressed sensing Chebyshev Chaos projection matrix; (2) extracting the morphological features-front and back RR intervals of the electrocardio signals; and (3) performing standardized processing on the electrocardio projection features and morphologic featuresand then feeding the processed features into a classifier to complete the electrocardio signal recognition process. Compared with the existing electrocardio signal recognition method, the electrocardio recognition method has the advantages that the 11-hour electrocardio signal data (108M) can be compressed to be 1M; the data storage space is greatly reduced; the calculation complexity degree is reduced; the electrocardio classified recognition can be performed at a higher speed; meanwhile, the recognition accuracy reaches 93.36 percent; and important significance is realized on real-time analysis and handling of heart diseases.

Description

technical field [0001] The invention relates to an electrocardiographic recognition method with extremely low data volume, which is used for feature extraction of electrocardiographic signals and belongs to the field of signal recognition. Background technique [0002] Compressed sensing theory is a new signal processing theory first proposed by Candes, Romberg, Tao and Donoho et al. The theory points out that as long as the signal is compressible or sparse in a certain transform domain, then a The transformation base incoherent projection matrix projects the high-dimensional signal to a low-dimensional space to achieve signal compression [0003] The ECG signal is a sparse signal, and the data compression of the signal can be realized through the projection matrix. Redundant information is removed during the compression process, which can reduce data storage space and computational complexity, which is conducive to the real-time processing of ECG signal recognition. [000...

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): G06K9/00
CPCG06F2218/08G06F2218/12
Inventor 李智彭韵陶李健
Owner SICHUAN UNIV
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