Electrocardiogram classification method of deep residual neural network based on attention mechanism

Abstract

The invention relates to an electrocardiogram classification method of deep residual neural network based on an attention mechanism. According to the invention, automatic classification of arrhythmia is realized by multi-lead ECG data and a deep residual neural network model based on the attention mechanism, firstly, the multi-lead ECG contains more ECG information than the single-lead ECG, and secondly, the depth residual network can learn characteristics of the model in a higher mode, which helps the model to converge, and finally, an attention mechanism module automatically enhances a feature map, improves the generalization ability of the model, and improves the learning efficiency of the network and the accuracy of ECG recognition.

Description

technical field [0001] The invention relates to the technical field of electrocardiogram classification, in particular to an electrocardiogram classification method based on a deep residual neural network of an attention mechanism. Background technique [0002] Electrocardiogram examination has become a common test item in hospitals. Electrocardiogram is the most basic indicator for doctors to judge the heart condition of patients. The electrocardiogram signal is a non-stationary periodic biological signal caused by the electrical activity of the heart, which contains a large amount of complex heart activity information, and only professionally trained doctors can accurately interpret it. Because of the complex structure of the heart and the regularity of heart activity, there are many types of arrhythmias. The electrocardiogram of the same type of arrhythmia in different stages of the same patient is likely to have obvious changes, and the difference in the electrocardiogr...

AI Technical Summary

Problems solved by technology

The ECG of the same type of arrhythmia in different stages of the same patient is likely to have obvious changes, and the difference in the ECG of the same type of arrhythmia in different patients is greater. Big problem, the generalization ability of ordinary convolutional neural network is limited, and the prediction ability of diseases with few samples is biased