Electrocardiogram feature recognition system and method

A feature recognition and electrocardiogram technology, applied in the field of electrocardiogram feature recognition system, can solve problems such as difficult positioning, P wave peak point, start and end point cannot be accurately positioned, and P wave is not obvious

Active Publication Date: 2017-08-08
SUZHOU INST OF NANO TECH & NANO BIONICS CHINESE ACEDEMY OF SCI
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the former method has advantages in finding the presence or absence of P waves and the range interval, but cannot accurately locate the specific peak points, start and end points of P waves
The latter method can accurately locate the peak point and the start and end points, but it is difficult to locate the P wave that is not obvious or slightly abnormal.

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
  • Electrocardiogram feature recognition system and method
  • Electrocardiogram feature recognition system and method
  • Electrocardiogram feature recognition system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0081] Please also refer to image 3 , replace the QRS wave and T wave range in the 12-lead ECG signal with the baseline BasicLine=0 in the pre-processing module 10 .

[0082] In this embodiment, the QRS and T wave ranges in the 12-lead ECG signal are replaced with the baseline BasicLine=0, which can exclude waves that have a greater impact on P wave identification.

[0083] For the ECG signal after replacing the QRS wave and T wave range in the ECG signal with the baseline BasicLine=0 in the pre-processing module 10, the data is organized according to the sampling points. The training data is organized into a matrix of 14862*13, and the test data is organized into a 14862*12 matrix. Since the test data does not include label categories, it is 12 columns.

[0084] In the classification module 20, libSVM is used for training and testing, and the training parameter is STemp=strcat('-s 0-c 1 -t 2 -g 0.09').

[0085] In the post-processing module 30, extract the starting point a...

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 present invention proposes an electrocardiogram feature recognition method that integrates domain knowledge and pattern recognition. First, pre-process the pre-processed ECG signal, and then use pattern recognition to separate the pre-processed signal into P wave, T wave or The characteristic points of the QRS wave, and then post-processing the results of pattern recognition, the purpose is to find the approximate range of the P wave, T wave or QRS wave, and finally use domain knowledge to determine the range of the P wave, T wave or QRS wave The start and end points and peak points of real P wave, T wave or QRS wave. It can effectively improve the feature extraction accuracy of P wave, T wave or QRS wave. The invention additionally provides an electrocardiogram feature recognition system.

Description

technical field [0001] The invention relates to an electrocardiogram feature recognition system and method, in particular to an electrocardiogram feature recognition system and method based on fusion of domain knowledge and pattern recognition. Background technique [0002] There is no doubt that electrocardiogram (ECG) is a necessary means for the diagnosis of cardiovascular diseases, and the automatic recognition of P wave, QRS wave and T(U) wave in ECG is also paid more and more attention. Complicated, at present, the recognition accuracy of P wave is low. [0003] There are two main types of existing P wave recognition, one is based on pattern recognition, that is, processing with a certain pattern recognition; the other is based on the P wave shape through the slope threshold or based on various changes (wavelet changes). Domain knowledge extracts P waves. Among them, the former method has advantages in finding the presence or absence of P waves and the range interval...

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): A61B5/0452
CPCA61B5/7246A61B5/349
Inventor 胡晓娟董军
Owner SUZHOU INST OF NANO TECH & NANO BIONICS CHINESE ACEDEMY OF SCI
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