Electrocardiosignal-based identity recognition method
An ECG signal and identity recognition technology, applied in the field of identity recognition, can solve problems such as the inability to effectively eliminate the difference of ECG signals and reduce the performance of ECG identity recognition, so as to improve the user experience, improve the recognition performance, and eliminate the differences. Effect
Pending Publication Date: 2022-08-02
山东光辉人力资源科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the currently proposed ECG signal identification analysis method based on time-frequency analysis cannot make a compromise between the performance and stability of ECG identification. Performance of electrical identification
In addition, ECG signals are easily affected by psychological factors and psychological factors. Different ECG signals of the same individual have differences at different times. The existing time-domain variation method belongs to the underlying feature extraction method, which can only extract ECG signal features one-sidedly. Can not effectively eliminate the difference of ECG signal
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
[0058] like figure 1 , figure 2 As shown in the present invention, an identification method based on ECG signals includes the following steps:
[0059] Step 1: Obtain and input the ECG signal, and perform noise elimination processing on the ECG signal. The noise elimination method is as follows:
[0060] Step 1. Select a method based on wavelet decomposition to remove the baseline drift noise of the ECG signal; specifically, use the DB8 biorthogonal wavelet to decompose the original ECG signal in 8 layers, and obtain the approximation coefficient and the detail coefficient of the ECG signal after decomposition, Since most of the signals reconstructed by the approximate coefficients of wavelet decomposition are baseline drift noise, the original ECG signal is subtracted from the signal reconstructed by the approximate coefficients to remove the baseline drift noise;
[0061] Step 2. Use the band-stop filter and the low-pass combined filter in turn to eliminate the power freq...
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 relates to an identity recognition method based on electrocardiosignals. Wherein hash transformation and a long-short term memory network learning model are mainly used, scattering transformation has translation invariance and local stability in the signal processing process, noise in electrocardiosignals can be effectively eliminated, and the stability of electrocardiosignal identity recognition can be effectively improved. In order to solve the problem that scattering representation belongs to shallow feature extraction and cannot effectively eliminate the difference of electrocardiosignals, according to the method, deep feature representation is extracted by using a mining mechanism of a deep learning model based on a long-short term memory network, so that the extracted features can have signal distinction among different individuals, and the difference of the electrocardiosignals is effectively eliminated; according to the method, through combination of a hash transform method and long and short term memory network learning, deep features and shallow features in the electrocardiosignals can be extracted, identification features of the electrocardiosignals can be extracted more effectively, and the performance of electrocardiosignal identity identification is improved.
Description
technical field [0001] The invention relates to the technical field of identification, in particular to an identification method based on an electrocardiogram signal. Background technique [0002] At present, although biometrics such as face and fingerprint have been widely used for personal identification, they are the external features of the human body, which are easy to be imitated and imitated in practical applications, and there are still shortcomings. The use of electrocardiograph (ECG) for identification has gradually attracted the attention of academia and industry. The main advantages of using ECG for identification are: 1. ECG signals can only be measured by fresh individuals; It is difficult to forge; 2. The ECG signal will not be lost due to external reasons, and it will exist for life; 3. The ECG signal is a one-dimensional signal with a small amount of data; 4. The ECG signal acquisition cost is low and the acquisition is convenient. [0003] ECG signals are ...
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 Applications(China)
IPC IPC(8): A61B5/346A61B5/352A61B5/00G06K9/00G06N3/04
CPCA61B5/346A61B5/352A61B5/7203A61B5/7225A61B5/726A61B5/725A61B5/7264A61B5/7267G06N3/044G06F2218/02G06F2218/08G06F2218/12
Inventor 苑光辉孙彬朱丰雪
Owner 山东光辉人力资源科技有限公司