Electrocardiogram signal classifying method based on one-dimensional convolutional neural network

Abstract

The invention relates to an electrocardiogram signal classifying method based on one-dimensional convolutional neural network. The method comprises the following steps: firstly, conducting denoising processing on an electrocardiogram signal by virtue of a wavelet fusion method; then, detecting an R wave peak point by a QRS wave group recognition algorithm based on biorthogonal spline wavelet, and completing division and dimensionality reduction of the electrocardiogram signal with the R point as a datum, so that a plurality of R wave candidate bands are obtained; then, establishing and optimizing an electrocardiogram signal oriented one-dimensional convolutional neural network model; and finally, with the processed R wave candidate bands as input data of the model, automatically completing characteristic extraction and classification of the electrocardiogram signal. The method provided by the invention, with the adoption of the wavelet fusion method, can simultaneously remove high-frequency noise and low-frequency noise, so that extracted signal characteristics are more conducive to recognition; by establishing the electrocardiogram signal oriented one-dimensional convolutional neural network model, the problem that electrocardiogram signal characteristic points must be precisely located is solved, and moreover, the problem that a conventional method, which selects an algorithm to extract characteristics firstly, and then selects an algorithm to complete classification, is complex in computation is solved.

Description

technical field [0001] The invention relates to the field of physiological signal classification and deep learning, in particular to a method for classifying electrocardiographic signals based on a one-dimensional convolutional neural network. Background technique [0002] As a chronic disease, cardiovascular disease has the characteristics of high risk, acute onset, and indistinct condition. It ranks first among all kinds of diseases and seriously threatens human health. It needs to be paid enough attention to. The traditional ECG signal classification method is to select the feature extraction method to extract the effective features of the signal, and then select the classification method to classify. However, this method requires the experimenter to accurately locate the feature points of the ECG signal, so as to ensure that high-quality signal features can be extracted, and then accurate classification results can be obtained. Although there are many studies on ECG sig...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method that can avoid the problem that the extracted features are sensitive to noise, avoid the problem of complex preprocessing of data, solve the problem that the traditional method must accurately locate the signal feature points, and ensure that A method to extract high-quality signal features

Images