Electrocardiogram signal detection method based on belief rule base and deep neural network

Abstract

The invention provides an electrocardiogram signal detection method based on a belief rule base and a deep neural network. The method comprises the following steps: constructing a deep neural networkmodel in accordance with input signals, selecting a network loss function and driving the deep neural network to conduct training in accordance with input data via the network loss function; extracting artificial characteristics via expert knowledge in accordance with the input signals; inputting the artificial characteristics as well as characteristics learned by the deep neural network, so as toconstruct the belief rule base, optimizing parameters of the belief rule base via an improved covariance matrix adaptive evolution strategy, and reducing rules in the belief rule base; and implementing decision fusion on judgment outputs of the deep neural network model and the belief rule base via a fusion method. The electrocardiogram signal detection method provided by the invention, through the full development of advantages of modeling based on expert experience knowledge and discovering complex patterns from mass data based on deep network learning, can automatically judge potential diseases, which may exist, in accordance with electrocardiogram signals of a tested object, so that obtained judgement is more robust and accurate.

Description

technical field [0001] The invention relates to the technical field of smart medical care, in particular to an electrocardiographic signal detection method based on a confidence rule base and a deep neural network. Background technique [0002] Most of the existing ECG diagnostic methods are judged by experienced doctors based on the tester's ECG signals. The doctor's medical knowledge and case experience are very important for the accuracy of the test. In recent years, automatic detection methods have also begun to appear, which can be mainly divided into two categories: methods based on expert systems and methods based on data-driven. The former is typically represented by the confidence rule base method, which first extracts the feature representation of the ECG signal, then designs rules based on expert experience and builds a confidence rule base, then performs parameter optimization and rule reduction, and finally applies the established confidence rule base Inferenc...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problems that the complexity of the existing ECG diagnosis method increases exponentially with the increase of the input feature dimension, and the generalization ability of the classifier is poor, the present invention proposes an ECG signal detection method based on a confidence rule base and a deep n

Images