Myocardial infarction detection method based on BiGRU depth neural network

A deep neural network and detection method technology, applied in the field of heart beat detection and classification, can solve problems such as difficult to use big data, achieve the effects of improving detection efficiency, effective deep learning classification, and improving accuracy
CN109846471AInactive Publication Date: 2019-06-07ZHENGZHOU UNIV
6 Cites 13 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ZHENGZHOU UNIV
Publication Date
2019-06-07
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a myocardial infarction detection method based on a BiGRU depth neural network. The method comprises the following steps: 1) data pretreatment: filtering baseline drift in anoriginal electrocardiosignal by using median filtering, filtering industrial frequency interference in the original electrocardiosignal by using a Butterworth digital band-stop filter, and filtering myoelectric interference by using a Chebyshev digital low-pass filter; 2) heart beat segmentation: detecting R wave peak value through dyadic spline wavelet transform, further calculating RR interval and extracting QRS wave group data; and 3) model training: carrying out depth learning classification on the waveform detected in the step 2) through the BiGRU depth neural network. The method has theadvantages of carrying out accurate detection and classification on myocardial infarction and effectively carrying out deep learning and classification on the electrocardiosignals.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of cardiac beat detection and classification, and in particular relates to a method for detecting myocardial infarction based on a BiGRU deep neural network. Background technique

[0002] Cardiovascular disease is one of the diseases that seriously threaten human health. In my country, cardiovascular disease is gradually becoming a high incidence. Myocardial infarction refers to the occurrence of atherosclerotic changes in the coronary arteries that nourish the myocardium. The cholesterol plaque deposited on the inner wall of the lumen falls off and forms a thrombus, which blocks a certain coronary artery and prevents a certain part of the myocardium from receiving blood supply for a long time. Myocardial infarction occurs. ischemia, injury or even necrosis. Myocardial infarction has a very high mortality and disability rate. In the past, myocardial infarction mostly occurred in the elderly in their 60s an...

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