Electrocardiosignal monitoring method, system and device and medium

Abstract

The invention provides an electrocardiosignal monitoring method, system and device and a medium. The electrocardiosignal monitoring method comprises the steps of obtaining an electrocardiosignal sample, carrying out segmentation according to the electrocardiosignal sample, and obtaining an electrocardiogram signal sample and cardiac impulse cycle features; carrying out wavelet transformation according to the electrocardiogram sample signal to obtain wavelet features; inputting the electrocardiogram signal sample, the cardiac impulse cycle features and the wavelet features into a first model toobtain an arrhythmia category; inputting the electrocardiogram signal sample, the cardiac impulse cycle features and the wavelet features into a second model to obtain a prediction data array; and performing visual display in combination with the arrhythmia category and the prediction data array. Compared with the existing ECG signal classification prediction method, the novel architecture constructed by wavelet transform and two learning models provided by the invention has higher performance, realizes light weight of the model, can realize offline processing, saves a large amount of cost, and can be widely applied to the technical field of signal analysis and processing.

Description

technical field [0001] The invention belongs to the technical field of signal analysis and processing, in particular to a monitoring method, system, device and medium of electrocardiographic signals. Background technique [0002] Electrocardiogram (ECG) is a technology that uses an electrocardiogram machine to record the electrical activity change pattern generated by each cardiac cycle of the heart from the body surface. The ECG signal has a stable characteristic, and in the prior art, there are a large number of cases where arrhythmia and other abnormal ECG signals are performed based on the ECG signal. However, the existing classification and prediction methods based on ECG signals cannot perform data processing in real time. If real-time processing of signals is required, the computing resources of the cloud or server are needed; the existing classification and prediction methods cannot realize offline processing, and use large models , the operation and maintenance wor...

AI Technical Summary

Problems solved by technology

However, the existing classification and prediction methods based on ECG signals cannot perform data processing in real time. If real-time processing of signals is required, the computing resources of the cloud or server are needed; the existing classification and prediction methods cannot realize offline processing, and use large models , the operation and maintenance work is complicated and the cost is high

Images