Key result
Combining Variational Mode Decomposition with a 1D-CNN substantially enhances ECG arrhythmia classification accuracy.
A novel deep learning approach combining Variational Mode Decomposition and a 1D-CNN improves the classification and recognition accuracy of cardiovascular diseases from long-duration ECG signals.
Continuous long duration Electrocardiogram (ECG) signals have demonstrated encouraging outcomes in the iden-tification and categorization of cardiovascular diseases. In this paper, we introduce an innovative method that combines Vari-ational Mode Decomposition (VMD) with a One-Dimensional deep Convolutional Neural Network (ID-CNN) for multiple heart disease classification. Firstly, we construct long duration ECG data from single heartbeat data, and each ECG signal is decomposed using VMD to remove mixed noise components, followed by reconstruction of the VMD-filtered signal. To reduce data dimensionality and accelerate model fitting, we employ maximum value sampling and linear normalization. Additionally, we employed a ID-CNN model for classification decision-making. We have validated the proposed algorithm using the MIT-BIH arrhythmia database, and the results demonstrate substantial en-hancement in ECG data classification and recognition accuracy.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2023) studied Cardiovascular disease (arrhythmia). Variational Mode Decomposition (VMD) combined with a 1D-CNN was evaluated on ECG data classification and recognition accuracy. A novel method combining Variational Mode Decomposition with a 1D-CNN demonstrated substantial enhancement in ECG data classification and recognition accuracy using the MIT-BIH arrhythmia database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: