Unlock instant, AI-driven research and patent intelligence for your innovation.

Abnormal ECG detection network training method, abnormal ECG early warning method and device

A technology for electrical anomaly detection and network training, applied in biological neural network models, alarms, diagnostic recording/measurement, etc., can solve problems such as high requirements for neural network hardware, inability to use mobile devices, and inability to effectively warn of sudden cardiac death. , to achieve the effect of small memory and reduced memory usage

Active Publication Date: 2022-05-24
BIOISLAND LAB +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Embodiments of the present invention provide a network training method for abnormal ECG detection, a method for early warning of abnormal ECG, a network training device for abnormal ECG detection, an early warning device for abnormal ECG, electronic equipment, and a storage medium, so as to solve problems that cannot be directly addressed in the prior art. Effective early warning of common sudden cardiac death, and the neural network used for early warning has high hardware requirements and cannot be applied to mobile devices

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
  • Abnormal ECG detection network training method, abnormal ECG early warning method and device
  • Abnormal ECG detection network training method, abnormal ECG early warning method and device
  • Abnormal ECG detection network training method, abnormal ECG early warning method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 This is a flow chart of the steps of a method for training an abnormality detection network for ECG provided in Embodiment 1 of the present invention. The embodiment of the present invention can be applied to training an abnormality detection network for detecting ECG to detect abnormality of the ECG. The ECG abnormality detection network training device can be implemented by hardware or software, and is integrated in the electronic equipment provided by the embodiment of the present invention, such as integrated on a computer device or a server, Specifically, as figure 1 As shown, the ECG abnormality detection network training method according to the embodiment of the present invention may include the following steps:

[0046] S101. Acquire an electrocardiogram signal of a patient with abnormal electrocardiogram and an electrocardiogram signal of a normal person.

[0047] In the embodiment of the present invention, before training, the ECG signal acquisition...

Embodiment 2

[0056] Figure 2A This is a flow chart of steps of a method for training an ECG abnormality detection network provided in Embodiment 2 of the present invention. This embodiment of the present invention is optimized on the basis of the foregoing Embodiment 1. Specifically, as Figure 2A As shown, the ECG abnormality detection network training method according to the embodiment of the present invention may include the following steps:

[0057] S201. Acquire an electrocardiogram signal of a patient with abnormal electrocardiogram and an electrocardiogram signal of a normal person.

[0058] S202. Perform denoising processing on the acquired electrocardiogram signal to obtain a denoised electrocardiogram signal.

[0059] In practical applications, the acquired electrocardiogram signal may contain at least one of EMG interference noise, baseline drift noise, and power frequency interference noise. , Eliminate the power frequency interference noise processing to obtain the denoised...

Embodiment 3

[0123] image 3 This is a flow chart of the steps of a method for early warning of abnormal electrocardiogram provided in the third embodiment of the present invention. The embodiment of the present invention can be applied to the situation of early warning of abnormal electrocardiogram. implementation, the ECG abnormality early warning device may be implemented by hardware or software, and integrated in the electronic device provided by the embodiment of the present invention, such as integrated on a mobile device, specifically, as image 3 As shown, the ECG abnormality early warning method according to the embodiment of the present invention may include the following steps:

[0124] S301. Acquire an electrocardiogram signal of the monitored person.

[0125] In this embodiment of the present invention, the person to be monitored may be a person at high risk of abnormal ECG, and the ECG signal of the person to be monitored may be collected through an ECG signal acquisition de...

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 embodiment of the present invention discloses a network training method for abnormal ECG detection, an ECG abnormality early warning method and a device. The training data is extracted from the received ECG signal; the training data is used to train the binary neural network as the ECG abnormality detection network, wherein the values ​​and weights of the nodes in the network layer are binary data, and the values ​​and weights of the nodes in the network layer are used to Perform a binary operation to obtain the node value of the next network layer. Since binary data occupies 1 bit of data, the memory usage is greatly reduced. Binary data can also be used for AND gate and XOR gate operations instead of multiplication, which can reduce the hardware overhead of the operating environment while performing fast operations, so that the training is good. The abnormal ECG detection network can be embedded in mobile devices with limited storage capacity and computing power, so as to directly and effectively warn various ECG abnormalities through mobile devices.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of electrocardiogram processing, and in particular, to an electrocardiogram abnormality detection network training method, an electrocardiogram abnormality early warning method, an electrocardiogram abnormality detection network training device, an electrocardiogram abnormality early warning device, electronic equipment and a storage medium. Background technique [0002] Sudden cardiac death (SCD) is one of the most important causes of death in cardiovascular diseases. Due to its concealment and suddenness, once a sudden cardiac death occurs, the survival rate of the patient is extremely low. It is a serious threat to human health, so early diagnosis and early warning are the keys to prevent SCD. [0003] In a solution of the prior art, one or more methods are selected in combination to compare and select the waveform detection algorithm with the best effect to detect and extract th...

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): A61B5/346A61B5/349
CPCA61B5/346G06N3/04G08B21/02A61B5/00
Inventor 王景峰黄凯陈样新张玉玲郭思璐宋日辉
Owner BIOISLAND LAB