Arrhythmia Recognition and Classification Method Based on Sparse Representation and Neural Network

A sparse representation and neural network technology, applied in character and pattern recognition, pattern recognition in signals, instruments, etc., to achieve the effect of reducing noise, improving classification accuracy, and reducing the dimension of features

Active Publication Date: 2022-04-22
XI AN JIAOTONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for identifying and classifying arrhythmia based on sparse representation and neural network, so as to solve the problem of separately considering the low-frequency band and high-frequency band of QRS wave proposed in the background technology, overcome the imbalance of sample categories, and improve the classification accuracy. question

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
  • Arrhythmia Recognition and Classification Method Based on Sparse Representation and Neural Network
  • Arrhythmia Recognition and Classification Method Based on Sparse Representation and Neural Network
  • Arrhythmia Recognition and Classification Method Based on Sparse Representation and Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] The present invention will be further described below in conjunction with drawings and embodiments.

[0080] like figure 1 As shown, the arrhythmia recognition and classification method based on sparse representation and neural network provided by the present invention comprises the following steps:

[0081] (1) In the preprocessing stage, a sparse representation framework based on dictionary learning is used for noise detection and filtering. This framework mainly includes two parts, the detection of different noises and the filtering of corresponding noises.

[0082] a) In the detection of noise, it mainly detects the common baseline drift, power frequency interference and electromyographic interference in the ECG signal. Baseline drift noise in ECG signal belongs to low frequency noise, while power frequency interference and EMG interference belong to high frequency noise. The specific steps are as follows:

[0083] 1) In this step, a moving average filter is use...

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 a method for identifying and classifying arrhythmia based on sparse representation and neural network. The method uses the sparse representation framework to preprocess the electrocardiographic signal, obtains the low-frequency part of the QRS wave, and then uses discrete cosine transform to realize the Feature extraction, using the principal component analysis to obtain the transformation coefficient after dimension reduction as the feature attribute, and finally using the Bagging algorithm with BP neural network as the base learner to complete the normal heart rhythm (N) and left bundle branch block ( LBBBB), right bundle branch block (RBBBB), atrial premature beat (APB), ventricular premature contraction (PVC) and paced beat (PB) for automatic classification. The invention extracts features from the low-frequency band of the QRS wave, reduces the dimension of feature attributes, and uses the Bagging algorithm in integrated learning to solve the problem of unbalanced categories, thereby improving the classification accuracy.

Description

technical field [0001] The invention belongs to the field of electrocardiographic signal analysis, in particular to a method for recognizing and classifying arrhythmia based on sparse representation and neural network. Background technique [0002] In recent years, with the rapid development of society and economy, profound changes have taken place in the lifestyle of the people, the prevalence of risk factors for cardiovascular disease in China is obvious, and the prevalence of cardiovascular disease continues to rise. In order to deal with this problem, the prevention and treatment of various cardiovascular diseases has become an important part of medical and health care. ECG signal is the main information to assist in the diagnosis of cardiovascular diseases, which has the characteristics of large amount of data, sensitivity to noise, and difficulty in analysis. Arrhythmia is a common symptom in cardiovascular diseases, and its accurate identification can assist in the t...

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): G06K9/00G06K9/62
CPCG06F2218/14G06F2218/06G06F2218/10G06F18/2136G06F18/2135
Inventor 王霞康春阳
Owner XI AN JIAOTONG 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