Ventricular premature beat identification method and device based on improved convolution neural network
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A convolutional neural network, ventricular premature beat technology, applied in the fields of medical science, sensors, diagnostic recording/measurement, etc., can solve the problem of low accuracy of ventricular premature beat heartbeat judgment, and achieve the effect of improving the judgment accuracy
Inactive Publication Date: 2019-04-16
SHANGHAI SID MEDICAL CO LTD
View PDF2 Cites 5 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to overcome the deficiencies of the prior art, the object of the present invention is to provide a method and device for recognizing premature ventricular beats based on an improved convolutional neural network, aiming to solve the problem of low accuracy in the automatic judgment of premature ventricular beats in the prior art
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment 1
[0073] Such as figure 1 with figure 2 As shown, the embodiment of the present invention provides a method for recognizing premature ventricular beats based on an improved convolutional neural network, including:
[0074] Preprocessing step S101, preprocessing the ECG signal;
[0075] The truncation step S102 is to truncate the ECG signal into several heartbeat sequences, and extract the RR interval between each heartbeat and the previous heartbeat;
[0076] Calculation step S103, calculating the kurtosis value and skewness value of each heartbeat sequence;
[0077] Recognition step S104, input the heartbeat sequence, RR interval, kurtosis value, and skewness value into the improved convolutional neural network model, output the recognition result of the heartbeat to be recognized, and determine whether the heartbeat to be recognized is premature ventricular beat according to the recognition result; The heartbeat to be identified includes the second heartbeat and all subseq...
specific Embodiment 2
[0101] Such as Figure 5 As shown, the embodiment of the present invention provides a premature ventricular beat recognition device based on an improved convolutional neural network, including:
[0102] A preprocessing module 201, configured to preprocess the ECG signal;
[0103] The truncation module 202 is used to truncate the ECG signal into several heartbeat sequences, and extract the RR interval between each heartbeat and the previous heartbeat;
[0104] Calculation module 203, for calculating the kurtosis value, skewness value of each heartbeat sequence;
[0105] The identification module 204 is used to input the heartbeat sequence, RR interval, kurtosis value, and skewness value into the improved convolutional neural network model, output the identification result of the heartbeat to be identified, and determine whether the heartbeat to be identified is premature ventricular contraction according to the identification result Heartbeat: the heartbeat to be identified i...
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 a ventricular premature beat identification method and a ventricular premature beat identification device based on an improved convolution neural network. The method comprisesthe following steps of: pretreating electrocardiosignal; cutting the electrocardiosignal into a plurality of heartbeat sequences, and extracting an RR interval between each heartbeat and a previous heartbeat; calculating a kurtosis value and bias value of each heartbeat sequence; inputting the above items into an improved convolution neural network model, outputting an identification result of a heartbeat to be identified, and judging whether the heartbeat to be identified is a ventricular premature heartbeat or not. The method adopts the improved convolution neural network, comprehensively considers a waveform characteristic of the heartbeat and the relationship between the heartbeat and the previous heartbeat, and automatically judges whether a certain heartbeat is a ventricular premature heartbeat or not, so that the judgment accuracy can be greatly improved. The improved convolution neural network consists of a convolution layer, a pool layer and a full-connection layer, wherein the full-connection layer is connected with specific characteristics of ventricular premature beats and sends the characteristics to a classifier after fusion calculation for automatically judging the ventricular premature beats.
Description
technical field [0001] The invention relates to the technical field of electrocardiographic signal processing, in particular to a method and device for recognizing premature ventricular beats based on an improved convolutional neural network. Background technique [0002] Premature ventricular contraction (PVC) is the premature ventricular excitation generated by ectopic pacemaker below the branch of His bundle, which can be seen in patients with organic heart disease and normal people without organic heart disease. Although sporadic ventricular premature beats seen in normal healthy people are not clinically important, but in the case of a tester suffering from a structural heart disease, it must be analyzed according to different situations and given necessary measures in combination with clinical symptoms and medical history. Treatment. [0003] Ventricular premature beats are mostly identified from the 24-hour ambulatory electrocardiogram due to their randomness. If it ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more