A method and system for extracting and classifying ECG signal features

Abstract

The present application provides a method and system for extracting and classifying ECG signal features. The main steps of the method include: (1) sequentially locating the R wave, Q wave, S wave, T wave and P wave of the ECG signal according to the adaptive threshold, (2) Taking the segmentation point between cardiac cycles as the starting point to slide and intercept 1-second ECG signals, the window length of the sliding window is 1 second, and the step size is one cardiac cycle. domain feature, obtain the morphological feature for the complete cardiac cycle signal included in the 1-second signal, (4) use rough set to do attribute reduction, and filter effective features as the input of discriminant network; the sliding window length and variable step size of the present invention The settings ensure that the complete cardiac cycle signal will not be truncated, combined with fixed-length and single-cycle methods to simultaneously obtain time-frequency domain features and morphological features in one signal detection, increasing the dimension of the feature set; using rough sets to attribute the feature set Reduction, improve the efficiency and accuracy of classification and discrimination.

Description

technical field [0001] The invention belongs to the field of electrocardiographic signal processing, and in particular relates to a method and system for extracting and classifying electrocardiographic signal features. Background technique [0002] Electrocardiographic signals (ECG) are widely used in clinical practice such as cardiovascular disease diagnosis and curative effect evaluation. Specifically, they can be used to diagnose arrhythmia, postoperative heart conditions, etc. Accurate feature extraction and effective classification are particularly important. [0003] At present, the feature extraction methods of ECG signals are mostly divided into two methods: fixed-length interception signal and single cardiac cycle interception signal. The fixed-length interception signal is to extract the fixed-length ECG separately, and the step size of the sliding window when extracting the signal is also fixed. This method can extract the time-frequency domain features in the si...

AI Technical Summary

Problems solved by technology

The fixed-length interception signal is to extract the fixed-length ECG separately, and the step size of the sliding window when extracting the signal is also fixed. This method can extract the time-frequency domain features in the signal, but it often truncates the signal of a complete cardiac cycle, resulting in Part of the single cardiac cycle signal is lost, the feature extraction is incomplete, and the fixed-length interception method cannot obtain the morphological characteristics of the signal waveform; the single cardiac cycle signal interception method can obtain the signal of the complete cardiac cycle, and can extract the morphological characteristics of the signal waveform within the cycle , but cannot obtain time-frequency domain features, both methods have their limitations

[0004] In addition, neural networks and support vector machines (SVM) are currently commonly used to classify signal features to determine the type of ECG signals. However, most current classification methods input all features into the classifier for discrimination, including irrelevant features, leading to classification. The efficiency is low, and the discrimination accuracy decreases

Images