Electrocardiosignal feature point detection method and system

A feature point detection and electrocardiographic signal technology, applied in the field of artificial intelligence data analysis, can solve the problems of difficult detection of P waves and T waves, and changeable shapes of P waves and T waves, so as to improve the robustness and accuracy. Effect

Pending Publication Date: 2021-10-12
济南汇医融工科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main method of QRS complex detection is to enhance the QRS of the ECG or weaken the intensity of the remaining waveforms according to the basic laws of the ECG signal and cardiac electrophysiological activities, and set the threshold for detection; The first method is the fixed window search method and the QRS-T elimination method, but it

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 feature point detection method and system
  • Electrocardiosignal feature point detection method and system
  • Electrocardiosignal feature point detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, a normal cardiac cycle is usually composed of P wave, QRS wave group and T wave. The analysis of the ECG is to find the QRS wave group first, because the QRS wave group is the most prominent feature in the ECG and is the basis for the detection of other waveforms. . According to the defects of the existing monitoring method described in the background technology, this embodiment proposes an automatic detection method of ECG signal feature points based on deep learning technology;

[0041] Deep learning is gradually being used in the detection of ECG signal feature points. Deep learning has strong self-learning ability and highly nonlinear mapping characteristics, and can learn ECG signal features from a large amount of training data. Currently, based on traditional machine learning The ECG feature point detection algorithm of the technology requires pre-specified thresholds or other assumptions. This embodiment proposes an automatic detection...

Embodiment 2

[0130] This embodiment provides a system for detecting ECG feature points, including:

[0131] A signal acquisition module configured to acquire ECG signals in continuous time;

[0132] The quality evaluation module is configured to evaluate the quality of the ECG signals in continuous time, and judge whether denoising processing is required;

[0133] The denoising module is configured to perform denoising processing on ECG signals in continuous time to correct baseline drift;

[0134] The segmentation processing module is configured to segment and process the ECG signals in continuous time to obtain standard ECG signal segments;

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 feature point detection method and system. The electrocardiosignal feature point detection method comprises the following steps: obtaining electrocardiosignals in continuous time; segmenting the electrocardiosignals in the continuous time to obtain standard electrocardiosignal segments; and extracting electrocardiosignal features are extracted from the standard electrocardiosignal segments based on a constructed one-dimensional coding and decoding deep learning model, carrying out waveform classification according to the electrocardiosignal features, and obtaining the detection result of each type of waveform boundary feature points according to the obtained waveform classification result. The electrocardiosignal features are automatically extracted by using the deep learning method, and the waveform classification of P waves, QRS waves, T waves and non-wavebands and detection of the boundary points of the P waves, the QRS wave groups and the T waves can be realized at the same time.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence data analysis, in particular to a method and system for detecting feature points of electrocardiographic signals. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The electrocardiogram captures the propagation process of electrical signals in the heart from the body surface, and displays the pathological state of the ventricles and atria through changes in waveform or rhythm. This type of equipment can perform real-time non-static ECG monitoring, but long-term ECG monitoring will generate a large number of ECG data. A normal cardiac cycle is usually composed of P wave, QRS wave group and T wave. The analysis of ECG is first to find the QRS wave group, because the QRS wave group is the most prominent feature in the ECG and is the basis for the det...

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
IPC IPC(8): A61B5/318A61B5/346A61B5/353A61B5/366A61B5/355A61B5/349A61B5/00
CPCA61B5/318A61B5/346A61B5/353A61B5/366A61B5/355A61B5/349A61B5/7203A61B5/725A61B5/7235A61B5/7267
Inventor 刘常春梁晓洪张明王吉阔
Owner 济南汇医融工科技有限公司
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