An electrocardiosignal enhancement and classification method based on a gated recurrent diffusion model

By generating ECG signal data using a gated recurrent diffusion model and combining it with a CNN-GRU classification model, the problems of data imbalance and insufficient capture of time series features in ECG signal classification are solved, thereby improving the recognition accuracy and classification performance of abnormal ECG signals.

CN119179929BActive Publication Date: 2026-07-03NANJING UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NANJING UNIV
Filing Date
2024-09-10
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing ECG signal classification models suffer from insufficient recognition capabilities and inadequate capture of time-series features when dealing with small-scale abnormal data and high data imbalance. Furthermore, they are highly dependent on preprocessing, leading to misdiagnosis or missed diagnosis.

Method used

We employ a gated recurrent diffusion model to generate new ECG signal data. This data is then combined with a CNN-GRU classification model and utilizes squeezed excitation blocks and multi-head attention mechanisms to enhance the dataset and capture local and global features.

Benefits of technology

It improves the recognition accuracy and classification performance of abnormal electrocardiogram signals, reduces the dependence on data volume, and enhances the robustness of the model and its ability to focus on key features.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119179929B_ABST
    Figure CN119179929B_ABST
Patent Text Reader

Abstract

The application provides an electrocardiosignal enhancement and classification method based on a gated recurrent diffusion model, comprising the following steps: step 1, obtaining an electrocardiosignal dataset; step 2, setting parameters and hyperparameters of the diffusion model; step 3, establishing a neural network structure of the diffusion model; step 4, training the diffusion model, and supplementing the electrocardiosignal dataset by using the trained diffusion model; step 5, setting hyperparameters of a classification model; step 6, establishing the classification model; and step 7, training the classification model by using the electrocardiosignal dataset obtained in step 4, and using the trained classification model for electrocardiosignal classification. The method introduces the gated recurrent diffusion model to supplement data, compared with a traditional generative model, can capture time sequence information of the electrocardiosignal, and thus simulate the characteristics of the heart rate.
Need to check novelty before this filing date? Find Prior Art