Electrocardiosignal identification and classification method based on Kernel-CNN

Abstract

The invention discloses an electrocardiosignal identification and classification method based on a Kernel-CNN. The method comprises the following steps: introducing kernel transformation into a convolution process to form a kernel transformation convolution operation so as to further enhance the model characteristic extraction ability; and performing verification based on data provided in an MIT-BIH database which is provided in MIT (Massachusetts Institute of Technology) to obtain a result, wherein the result proves that compared with the convolutional neural network, the model disclosed by the invention has a lower LOSS value on the same prediction correct rate. The convolutional neural network disclosed by the invention has the outstanding characteristic extraction ability; and throughintroducing the kernel transformation into the convolution operation, nonlinear mapping of data is realized, so that the characteristic extraction ability in the convolution process is further enhanced. After an electrocardiosignal is input into a trained network, probability values of five types can be obtained, and the maximum probability value is selected as the type of the data. Prior knowledge of signals is not needed to be verified firstly by using the signal, input of specialists is also not needed, and effective characteristics can be extracted from the electrocardiosignal, and thus, the electrocardiosignal can be applied to identification and classification of an electrocardiogram through medical treatment instruments.

Description

technical field [0001] The invention belongs to the technical field of medical devices, relates to intelligent recognition of electrocardiographic signals in medical devices, and in particular to a method for recognizing and classifying electrocardiographic signals based on Kernel-CNN. Background technique [0002] According to the latest report of the World Health Organization (WHO) in 2019, cardiovascular disease (CVD) is one of the main diseases that cause human death. The high mortality rate of cardiovascular disease makes it continue to affect our normal life. The prevention, diagnosis and treatment of cardiovascular diseases have become important issues that society needs to solve. [0003] The automatic classification technology of electrocardiosignal (ECG) can be summarized as: signal acquisition, preprocessing, feature extraction and classification. Throughout the process, feature extraction plays a vital role and can directly affect the final classification result...

AI Technical Summary

Problems solved by technology

These methods require certain prior knowledge of the signal and often require expert input, which limits the application of the method

Images