Method and system for identifying atrial fibrillation electrocardiosignals through weighted multi-scale limited penetrable visibility graph
A technology of ECG signal and identification method, which is applied in the field of weighted multi-scale finite traversal visual image identification of atrial fibrillation ECG signal, can solve the problems of irregular RR intervals and difficulty in obtaining clean data, and achieve improved accuracy and results Enhanced effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0041] Such as figure 1 As shown, the method for identifying atrial fibrillation ECG signals in the weighted multi-scale limited traversing visual image of this embodiment specifically includes:
[0042] Step S101: Obtain an ECG signal of a set length.
[0043] For example, the electrocardiographic signal of this embodiment is taken from the 2017 PhysioNet / Cinc Challenge, and the electrocardiographic signal of each patient is recorded. According to the waveform and rhythm of the ECG signal, identify the ECG of patients with atrial fibrillation. The ECG categories include: normal rhythm, atrial fibrillation rhythm, other rhythms and noise records.
[0044] This example contains 8528 single-lead ECG records ranging in duration from 9 seconds to just over 60 seconds. The ECG was sampled at 300Hz and band-pass filtered. Each piece of data includes a signal record and the category corresponding to the signal, and the category is shown in Table 1.
[0045] Table 1 ECG waveform s...
Embodiment 2
[0110] Such as Figure 5 As shown, the present embodiment provides a system for identifying atrial fibrillation ECG signals with weighted multi-scale limited traversal visual images, which specifically includes the following modules:
[0111] An electrocardiographic signal acquisition module, which is used to acquire an electrocardiographic signal of a set length;
[0112] An original feature extraction module, which is used to extract the original features of the ECG signal to obtain a corresponding original feature vector;
[0113] A network feature extraction module, which is used to convert the electrocardiographic signal into a network form, extract corresponding network features, and obtain corresponding network feature vectors;
[0114] The electrocardiographic signal identification module is used to input the original feature vector and the network feature vector into the machine learning model to obtain the category identification result of the electrocardiographic s...
Embodiment 3
[0117] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method for identifying an atrial fibrillation electrocardiogram as described above are implemented.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com