Automatic arrhythmia analysis method based on channel signal fusion neural network
A neural network, arrhythmia technology, applied in the field of medical signal processing, can solve the problem that the arrhythmia analysis system is not enough to meet the accuracy requirements
Active Publication Date: 2021-07-20
YANTAI YIZHONG MEDICAL SCI & TECH CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to solve the problem that the existing arrhythmia analysis system is not enough to meet the accuracy requirements of clinical applications, and to provide an automatic arrhythmia analysis method based on channel signal fusion neural network
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 1
[0023] Example 1 Automatic arrhythmia analysis method based on depth neural network
[0024] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.
[0025] Specific examples are internationally connected ECG Database MIT-BIH ARRHYTHMIA DATABASE (Mitdb), the data and instructions of the database are disclosed in the industry's well-known physionet.org website; the database contains 47 patients two-leading way half an hour 360Hz electrocardiogram record, It has passed the manual label of heart disease. From the data set, four cardios are selected as the effect assessment basis, including N-class (normal heart shot or branch transduction resistance ", Class S Alternative unusual heart shot), V-class (ventricular abnormal heart shot), class f-class (merged heart shot); these four categories of labels and corresponding relationships with Mitdb data concentration are in Table 1; in this example, work in computer The M...
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 invention discloses an automatic arrhythmia analysis method based on channel signal fusion deep neural network, which includes: generating multi-channel electrocardiogram samples by two sampling methods; When it is two leads, it is equivalent to forming a 4*600*1-dimensional ECG signal sample, inputting the input signals of the four channels into the merge layer and merging along the last dimension, and the merge layer outputs a 600*4-dimensional signal . Two layers of convolutional layer units are connected in series after merging layers, and there is an attention layer between the convolutional layer unit and the LSTM layer unit; the convolutional layer unit includes a convolutional layer that uses one-dimensional convolution to extract one-dimensional ECG signal features and a sequentially connected one Incentive unit operation and one pooling layer operation; LSTM layer unit is connected in series with a fully connected layer whose excitation unit is softmax; output; learn the parameters of deep neural network, and automatically identify samples; solve the problem that the existing arrhythmia analysis system is not enough The problem of meeting the accuracy requirements of clinical applications.
Description
Technical field [0001] The present invention relates to the field of medical signal processing, and more particularly, the present invention relates to an automatic arrhythmia analysis method based on a channel signal fusion neural network. Background technique [0002] In recent years, the auxiliary diagnostic equipment for ECG is developed rapidly. With the scientific and technological progress in the information, especially with the progress of pattern identification technology, the function of the electrocardiographic equipment is no longer just acquiring ECG signals, prints the electrocardiogram, but Excavate the effective data in the electrocardiogram and automatic identification, and statistical heartbeat information. Analytical equipment with automatic identification of heartbeat features can provide a more intuitive and effective electrocardiogram information, effectively saving diagnostic time, enhancing the doctor's diagnostic efficiency, is one of important auxiliary ...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/20G06N3/04
CPCG16H50/20G06N3/045
Inventor 刘通危义民臧睦君邹海林贾世祥柳婵娟周树森
Owner YANTAI YIZHONG MEDICAL SCI & TECH CO LTD