Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/24237
Title: | ECG Recurrence Plot-Based Arrhythmia Classification Using Two-Dimensional Deep Residual CNN Features |
Authors: | Mathunjwa, BM Lin, YT Lin, CH Abbod, MF Sadrawi, M Shieh, JS |
Keywords: | electrocardiogram;arrhythmia;recurrence plot;deep residual convolutional neural network |
Issue Date: | 20-Feb-2022 |
Publisher: | MDPI AG |
Citation: | Mathunjwa, B.M., Lin, Y.T., Lin, C.H., Abbod, M.F., Sadrawi, M. and Shieh, J.S. (2022) ‘ECG Recurrence Plot-Based Arrhythmia Classification Using Two-Dimensional Deep Residual CNN Features’, Sensors, 22 (4), 1660, p. 1-26. doi:10.3390/s22041660. |
Abstract: | Copyright: © 2022 by the authors. In this paper, an effective electrocardiogram (ECG) recurrence plot (RP)-based arrhythmia classification algorithm that can be implemented in portable devices is presented. Public databases from PhysioNet were used to conduct this study including the MIT-BIH Atrial Fibrillation Database, the MIT-BIH Arrhythmia Database, the MIT-BIH Malignant Ventricular Ectopy Database, and the Creighton University Ventricular Tachyarrhythmia Database. ECG time series were segmented and converted using an RP, and two-dimensional images were used as inputs to the CNN classifiers. In this study, two-stage classification is proposed to improve the accuracy. The ResNet-18 architecture was applied to detect ventricular fibrillation (VF) and noise during the first stage, whereas normal, atrial fibrillation, premature atrial contraction, and premature ventricular contractions were de-tected using ResNet-50 in the second stage. The method was evaluated using 5-fold cross-validation which improved the results when compared to previous studies, achieving first and second stage average accuracies of 97.21% and 98.36%, sensitivities of 96.49% and 97.92%, positive predictive values of 95.54% and 98.20%, and F1-scores of 95.96% and 98.05%, respectively. Furthermore, a 5-fold improvement in the memory requirement was achieved when compared with a previous study, making this classifier feasible for use in resource-constricted environments such as portable devices. Even though the method is successful, first stage training requires combining four different arrhyth-mia types into one label (other), which generates more data for the other category than for VF and noise, thus creating a data imbalance that affects the first stage performance. |
Description: | Data Availability Statement: This study utilizes the publicly available dataset, from https:// physionet.org, accessed on 22 June 2020. |
URI: | https://bura.brunel.ac.uk/handle/2438/24237 |
DOI: | https://doi.org/10.3390/s22041660 |
Other Identifiers: | 1660 |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | 3.06 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License