Electrocardiogram signal processing method and device

Abstract

The embodiment of the invention discloses an electrocardiogram signal processing method and device. The method comprises the steps of denoising sample data including a reference characteristic type electrocardiogram signal to obtain a filter electrocardiogram signal, wherein the sample data includes sample data for training and sample data for test, extracting characteristics of the filter electrocardiogram signal on the basis of a multi-electrocardiogram period fusion method to obtain a characteristic electrocardiogram signal, carrying out data normalization treatment on the characteristic electrocardiogram signal to obtain a standard electrocardiogram signal, training a BP neural network according to the standard electrocardiogram signal corresponding to the sample data for training to obtain a trained BP neural network, injecting the standard electrocardiogram signal corresponding to the sample data for test into the trained BP neural network, and acquiring a classification result of a standard signal corresponding to the sample data for test. By adopting the electrocardiogram signal processing method and device disclosed by the embodiment, the comprehensiveness and accuracy for extracting and classifying the characteristic electrocardiogram signals can be improved.

Description

technical field [0001] The present invention relates to the technical field of signal processing, in particular to a method and device for processing electrocardiographic signals. Background technique [0002] The ECG signal is the comprehensive performance of the electrical activity of the heart on the body surface. The purpose of ECG signal processing is to infer the state of the cardiovascular system based on the characteristics of the ECG signal, and make auxiliary medical decisions accordingly. [0003] ECG signal processing method includes two parts, ECG signal feature extraction and classifier design. The feature extraction of ECG signals mainly includes wavelet transform method and feature parameter estimation method, but the above methods only perform feature extraction for important feature bands in one ECG cycle. In terms of classifier design, there are mainly support vector machines, linear judgment and automatic Tissue mapping, among the above ECG signal proce...

AI Technical Summary

Problems solved by technology

The feature extraction of ECG signals mainly includes wavelet transform method and feature parameter estimation method, but the above methods only perform feature extraction for important feature bands in one ECG cycle. In terms of classifier design, there are mainly support vector machines, linear judgment and automatic Tissue mapping, among the above ECG signal processing methods, the comprehensiveness and accuracy of feature ECG signal extraction and classification need to be improved

Images