A Parallel Cross Convolutional Recurrent Neural Network for Automatic Imbalanced ECG Arrhythmia Detection with Continuous Wavelet Transform
Open Access
Abstract
Automatic detection of arrhythmia using electrocardiogram (ECG) and deep learning (DL) is very important to reduce the global death rate from cardiovascular diseases (CVD). Previous studies on automatic arrhythmia detection relied largely on various ECG features and have achieved considerable classification accuracy using DL-based models. However, most previous research has ignored multi-class imbalanced problems in ECG arrhythmia detection. Therefore, it remains a challenge to improve the classification performance of the DL-based models. This paper proposes a novel parallel cross convolutional recurrent neural network in order to improve the arrhythmia detection performance of imbalanced ECG signals. The proposed model incorporates a recurrent neural network and a two-dimensional (2D) convolutional neural network (CNN) and can effectively learn temporal characteristics and rich spatial information of raw ECG signals. Continuous wavelet transform (CWT) is used to transform the ECG signals into a 2D scalogram composed of time–frequency components, and subsequently, the 2D-CNN can learn spatial information from the 2D scalogram. The proposed model is not only efficient in learning features with imbalanced samples but can also significantly improve model convergence with higher accuracy. The overall performance of our proposed model is evaluated based on the MIT-BIH arrhythmia dataset. Detailed analysis of evaluation metrics reveals that the proposed model is very effective in arrhythmia detection and significantly better than the existing hierarchical network models.Keywords
Funding Information
- National Research Foundation of Korea (2016R1A5A1012966, 2021R1F1A1062285)
This publication has 37 references indexed in Scilit:
- Heartbeat classification using disease-specific feature selectionComputers in Biology and Medicine, 2014
- Heartbeat Classification Using Morphological and Dynamic Features of ECG SignalsIEEE Transactions on Biomedical Engineering, 2012
- Optimization of ECG Classification by Means of Feature SelectionIEEE Transactions on Biomedical Engineering, 2011
- Temporal lobe seizure prediction based on a complex Gaussian waveletClinical Neurophysiology, 2011
- A new method for classification of ECG arrhythmias using neural network with adaptive activation functionDigital Signal Processing, 2010
- Learning from Imbalanced DataIEEE Transactions on Knowledge and Data Engineering, 2009
- Multilead Analysis of T-Wave Alternans in the ECG Using Principal Component AnalysisIEEE Transactions on Biomedical Engineering, 2009
- Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval FeaturesIEEE Transactions on Biomedical Engineering, 2004
- Support Vector Machine-Based Expert System for Reliable Heartbeat RecognitionIEEE Transactions on Biomedical Engineering, 2004
- The impact of the MIT-BIH Arrhythmia DatabaseIEEE Engineering in Medicine and Biology Magazine, 2001