Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for classifying electrocardiosignals by using optimized AdaBoost weighting mode and weak classifier

A weak classifier, electrocardiographic signal technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problems of weak classifiers without considering the wrong sample misclassification rate, low accuracy, etc., to improve the screening method, Good classification, obvious effect of classification

Pending Publication Date: 2020-08-21
JIANGNAN UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing ECG signal classification using the AdaBoost algorithm adjusts the weights in the training set through the misclassification rate of the weak classifier, and all misclassified ECG signal samples are weighted with the same weighting factor, without considering The misclassification rate of the wrong sample is used to screen the weak classifier, and the classification accuracy of this classification method is not high

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
  • Method for classifying electrocardiosignals by using optimized AdaBoost weighting mode and weak classifier
  • Method for classifying electrocardiosignals by using optimized AdaBoost weighting mode and weak classifier
  • Method for classifying electrocardiosignals by using optimized AdaBoost weighting mode and weak classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Such as figure 1 , figure 2 Shown, a kind of method utilizing optimized AdaBoost weighting mode and weak classifier to ECG signal classification, described method comprises:

[0040] S1: Obtain ECG data, the data set comes from the arrhythmia database in the MIT-BIH database (the database for researching arrhythmia provided by the Massachusetts Institute of Technology);

[0041] S2: Carry out ECG data feature extraction, described feature extraction algorithm is discrete wavelet transform (DWT), is specifically binary wavelet transform, concrete steps are as follows:

[0042] S201: Take the first 500 sampling points to ensure the data volume of the preprocessed ECG signal;

[0043] S202: Set the positive threshold to be 1 / 4 of the average value of the maximum value point amplitude, and the negative threshold value to be 1 / 4 of the average value of the minimum value point amplitude value;

[0044] S203: The function selects a quadratic B-spline wavelet with a scale o...

Embodiment 2

[0063] This embodiment verifies the improved algorithm.

[0064] Binary classification algorithms often use the ROC (Receiver Operating Characteristic) curve and AUC (Area Under the Curve) value to judge the performance of the classifier; the specific process is: divide the two types of samples into positive and negative, and use the model The correctly classified samples are denoted by TP, the positive class misclassified samples are denoted by FP; the negative class misclassified samples are denoted by TN, and the negative class misclassified samples are denoted by FN. Such as Figure 4 As shown, the abscissa of the curve is False positive rate (FPR), and the ordinate is True positive rate (TPR). The AUC value refers to the area enclosed by the ROC curve and the false positive rate (FPR) on the abscissa.

[0065]

[0066]

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

No PUM Login to View More

Abstract

The invention discloses a method for classifying electrocardiosignals by using an optimized AdaBoost weighting mode and a weak classifier, and belongs to the technical field of data source classification. The method comprises the steps: conducting feature extraction on electrocardiogram data to obtaining an electrocardiogram signal training sample data set; according to the initial weight of the electrocardiosignal sample, sampling and selecting an electrocardiosignal training data set to obtain the electrocardiosignal sample; using the weak classifier for classifying electrocardiosignal samples, wherein the weighting mode of the samples which are wrongly classified is determined by the classification error rate of the weak classifier and the probability that the samples are wrongly classified. According to the method, the misclassification probability of misclassification samples is fully considered, and the weak classifier is screened by setting a proper threshold value, so that thestrong classifier with higher classification precision is obtained.

Description

technical field [0001] The invention relates to a method for classifying electrocardiographic signals by using an optimized AdaBoost weighting method and a weak classifier, and belongs to the technical field of data source classification. Background technique [0002] The AdaBoost algorithm originated in 1990. Schapire proposed the Boosting (bootstrapping) algorithm, which is an effective tool to improve the prediction ability. However, the Boosting algorithm cannot solve the problem of how to synthesize weak classifiers into strong classifiers. In 1995, Freund and Schapire proposed the AdaBoost algorithm, which is an iterative algorithm, which obtains the corresponding weak classifier through the sample distribution and the weight of the weak classifier, and forms a strong classifier, which has high precision and It has been widely used in classification problems and regression problems. At present, it is mainly used in bioelectrical signal processing, face recognition, ima...

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
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62
CPCG06F2218/12G06F18/214Y02A90/10
Inventor 虞致国王恬魏敬和顾晓峰
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com