Method and device for generating heart beat data sample classification network
A technology for classifying networks and data samples, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as insufficient deep learning
Active Publication Date: 2020-06-19
SHANGHAI YOCALY HEALTH MANAGEMENT CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the ECG data, common heartbeat types, such as "normal", "atrial premature beats", "ventricular premature beats", etc., can obtain tens of thousands or even millions of heartbeat fragments, which belong to large sample data and can meet training requirements. The needs of deep learning network; uncommon heartbeat types, such as "ventricular flutter", "ventricular fibrillation", etc., generally only a few hundred heartbeat fragments can be collected, which belongs to small sample data, which is far from enough for deep learning
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0063] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments . Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0064] The artificial intelligence convolutional neural network (Convolutional Neural Network, CNN) model is a deep learning model, and its essence is a multi-level network connection structure that simulates a neural network. Including: convolution layer (ConvolutionLayer), activation function (Relu), pooling layer (Pooling Layer) and full connection layer (Full Connection Layer). Using this learning model, the input data is sequentially ...
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
Login to View More Abstract
The embodiment of the invention relates to a method and device for generating a heart beat data sample classification network, and the method comprises the steps: carrying out the large sample screening of a first batch of sample data sequences to generate a large sample data sequence, and carrying out the small sample screening of the first batch of sample data sequences to generate a small sample data sequence; performing convolutional network training processing on the feature extraction network and the classification network based on the large sample data sequence to generate a large sample feature extraction network and a large sample classification network; performing convolutional network training processing on the large sample feature extraction network based on the small sample data sequence to generate a small sample classification network; and combining the small sample classification network and the large sample classification network to generate a heart beat data sample classification network. The embodiment of the invention further relates to a heart beat data identification method and device based on the heart beat data sample classification network. The heart beat data sample classification network is used for carrying out heart beat type identification on the real-time heart beat data.
Description
technical field [0001] The invention relates to the technical field of electrocardiographic signal processing, in particular to a method and device for generating a heartbeat data sample classification network. Background technique [0002] ECG data is a group of electrical signal data related to the cardiac cycle of the heart collected by the electrocardiograph through body surface electrodes, and ECG analysis is to analyze the characteristics of the collected ECG data. The method of using deep learning to intelligently analyze ECG data is to input batch feature ECG data as sample data into the convolutional neural network for network learning and training to generate a feature classification model, and then use the classification model to detect and classify the collected real-time ECG data . Therefore, in the process of deep learning, sufficient data volume is crucial for network learning and training. But in the medical field, insufficient data is very common. In the ...
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
Login to View More IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/12G06F18/2415G06F18/214Y02A90/10
Inventor 吴泽剑曹君
Owner SHANGHAI YOCALY HEALTH MANAGEMENT CO LTD