A composite feature extraction method and corresponding monitoring system for multi-lead ECG signals
A technology of composite features and extraction methods, applied in applications, telemetry patient monitoring, diagnostic recording/measurement, etc., can solve the problem of low system monitoring accuracy and the inability to accurately detect local small short-term dynamic changes of ECG signals and complex ECG waveform shape changes To achieve the effect of improving comprehensiveness and accuracy, enhancing feature expression ability, and efficient and accurate monitoring
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0092] A method for extracting composite features of multi-lead ECG signals, comprising the steps of:
[0093] Step 1: extracting the statistical features of the morphology of the single-lead ECG signal;
[0094] Step 2: Repeat step 1 to obtain the statistical characteristics of the morphology of all leads, and then fuse the obtained statistical characteristics of the morphology of all the leads;
[0095] The statistical feature extraction of morphology includes the following steps:
[0096] Step a1: Take a certain cardiac beat in the single-lead ECG signal {X(t),t=1,...,N}, and locate the starting point, ending point and T wave ending point of its QRS wave as (x1,X (x1)), (x2, X(x2)) and (x3, X(x3)), then the QRS band can be expressed as Y1={X(t),t=x1,...,x2}, ST-T segment It can be expressed as Y2={X(t),t=x2,...,x3};
[0097] Step a2: Calculate the area C1, kurtosis coefficient C2, skewness coefficient C3 and standard deviation C4 of the QRS band:
[0098]
[0099] ...
Embodiment 2
[0120] A method for extracting composite features of multi-lead ECG signals, comprising the steps of:
[0121] Step 1: Extract the statistical features and wavelet energy entropy features of the morphology of the single-lead ECG signal;
[0122] Step 2: Repeat step 1 to obtain the statistical features and wavelet energy entropy features of all leads, and then fuse the obtained statistical features and wavelet energy entropy features of all leads;
[0123] The corresponding system differences are as follows:
[0124] Feature extraction module, for extracting the morphological statistical features or morphological statistical features and wavelet energy entropy features of each lead ECG digital signal after the separation;
[0125] The feature extraction module includes a dynamic link library, a feature extraction unit and a feature fusion unit,
[0126] A dynamic link library for encapsulating the feature extraction unit;
[0127] The feature extraction unit is used to call ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


