Atrial premature beat target detection method based on convolutional neural network
A convolutional neural network, target detection technology, applied in the field of ECG detection, can solve the problem of not being able to judge the type of arrhythmia and give location information at the same time
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0020] This embodiment provides a method for detecting atrial premature beats based on a convolutional neural network, such as figure 1 shown, including:
[0021] Step 1, collect a number of ECG signals that contain atrial premature beats and have marked R waves;
[0022] Step 2, through data preprocessing, label each ECG signal with a data label, and form a training set with the ECG signal data labeled with the data label, the data label includes the heartbeat type and heartbeat at different sampling points of the ECG signal Location;
[0023] Step 3, using the electrocardiographic signal data in the training set as input, and taking the heart beat type and position at different sampling points of the electrocardiographic signal as output to train the convolutional neural network model;
[0024] Step 4. Obtain real-time ECG data to be detected, and input the trained convolutional neural network model to predict the type and location of abnormal heart beats, so as to realize...
Embodiment 2
[0059] A second embodiment of the present invention provides a computer storage medium, on which a computer program is stored, and the computer program is used to implement the detection method described in embodiment 1 when executed by a processor.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


