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

ECG signal processing method for arrhythmia classification

A technology for arrhythmia and signal processing, applied in the field of biomedicine, can solve the problem of low classification accuracy of arrhythmia, achieve the effect of avoiding inter-individual differences and intra-individual differences, high classification accuracy, and convenient use

Active Publication Date: 2019-04-05
NORTHWESTERN POLYTECHNICAL UNIV
View PDF9 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides an ECG signal processing method for arrhythmia classification to solve the problem of low accuracy of arrhythmia classification

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
  • ECG signal processing method for arrhythmia classification
  • ECG signal processing method for arrhythmia classification
  • ECG signal processing method for arrhythmia classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution in the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention and the accompanying drawings.

[0024] Such as figure 1 Shown, a kind of ECG signal processing method facing arrhythmia classification, comprises the following steps:

[0025] S1: Perform preprocessing operations such as R peak detection, heartbeat extraction, and data balance on the ECG to obtain ECG signal segments with a uniform format.

[0026] The R peak is the most obvious sign of a heartbeat in the ECG signal, so the position of the R peak can be used to represent the moment when each heartbeat occurs. In the embodiment of the present invention, the popular Pan-Tompkins algorithm is used for R-peak detection. Then, taking the moment of R peak as the center, select an appropriate number of sampling points ...

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 provides an ECG signal processing method. ECG signals can be analyzed from a plurality of time-frequency resolutions, and SB-LSTM and TD-CNN are separately utilized to mines the overallfluctuation pattern and local fluctuation pattern of signals from ECG sub-layer signals, and a Sum Rule is finally used for fusing the intermediate classification results of each ECG sub-layer to obtain more accurate and robust classification results. The ECG signal processing method avoids individual differences and intra-individual differences caused by manual classification, and can obtain thestable classification results; and in addition, the ECG signal processing method does not need any expert knowledge, does not need to manually design various features, does not need to perform featureselection processing, does not need to separately construct classifiers, is a typical end-to-end method, and has the characteristics of convenient use, high classification accuracy and the like.

Description

technical field [0001] The invention relates to the field of biomedicine, in particular to an ECG signal processing method for arrhythmia classification. Background technique [0002] "Arrhythmia" means the heart beats faster or slower than normal. Many arrhythmias do not have any symptoms. There are five types of arrhythmia: non-ectopic (N: Non-ectopic), ventricular ectopic (V: Ventricular ectopic), supraventricular ectopic (S: Supraventricular ectopic), mixed (F: Fusion), unknown (Q: Unknown). Cardiac activity patterns vary greatly between individuals, and even in the same individual at different time periods, making accurate classification of arrhythmias extremely difficult. [0003] The existing arrhythmia classification methods are mainly divided into two categories: 1) manual classification methods based on professional doctors; 2) computer-aided classification methods based on feature extraction, feature selection and classifier construction. The former requires d...

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): A61B5/0452A61B5/024A61B5/0245
CPCA61B5/02405A61B5/0245A61B5/35
Inventor 周兴社刘帆王柱於志文倪红波
Owner NORTHWESTERN POLYTECHNICAL UNIV
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