Arrhythmia classification method based on multi-feature fusion and Stacking-DWKNN

Abstract

The invention relates to an arrhythmia classification method based on multi-feature fusion and Stacking-DWKNN. The arrhythmia classification method comprises the following steps: S1, removing noise inan electrocardiosignal by adopting continuous wavelet transform; S2, segmenting the electrocardiosignal processed in the step S1 to intercept a complete heart beat, then performing feature extractionon the intercepted heart beat, and establishing the following data sets for the extracted features according to categories, wherein the set A = {235 single heart beat morphological characteristics},the set B = {P-QRS-T wave}, the set C = {PR interval}, the set D = {QT interval}, the set E = {ST segment}, the set F = {RR interval}, the set G = {R amplitude}, and the set H = {T amplitude}; S3, inputting any one set or a combination of any multiple sets in the data set in the step S2 into a plurality of KNN algorithms which are integrated by Stacking and improved by weight values for heart beatclassification. The heart beat classification method provided by the invention can effectively improve the result accuracy of heart beat classification.

Description

technical field [0001] The invention belongs to the technical field of arrhythmia classification methods, and is an arrhythmia classification method based on multi-feature fusion and Stacking-DWKNN. Background technique [0002] The electrocardiogram (ECG) is a non-invasive, inexpensive and well-established diagnostic tool that is widely used in a variety of applications. It represents changes in the electrical activity of the heart over time and contains basic physiological information widely used to analyze cardiac function, which is important for the detection of cardiac arrhythmias. Most arrhythmias are harmless, but some can be life-threatening immediately. Therefore, accurate detection of cardiac arrhythmias in patients plays a vital role in the prevention of cardiovascular diseases. The electrocardiogram (ECG) has the advantages of easy acquisition and low equipment cost, and can be used to judge whether the arrhythmia is sinus or ectopic, and is an important basis ...

AI Technical Summary

Problems solved by technology

However, under different conditions, there are significant differences in the morphology and temporal characteristics of ECG signals, and some arrhythmias only occasionally occur in patients' daily life, requiring the use of dynamic electrocardiography to record long-term ECG activity

Traditional Holter analysis is done manually, but manual beat-by-beat manual analysis of long-term ECGs is time-consuming and impractical

Images