Convolutional neural network optimized by differential evolution for electrocardiogram classification

Wang Shir Li

QR Code Link :
Type :	article
Subject :	Q Science
ISSN :	1380-7501
Main Author :	Wang Shir Li
Title :	Convolutional neural network optimized by differential evolution for electrocardiogram classification

Place of Production :	Tanjung Malim
Publisher :	Fakulti Komputeran dan Meta Teknologi
Year of Publication :	2023
Notes :	Multimedia Tools and Applications
Corporate Name :	Universiti Pendidikan Sultan Idris
HTTP Link :	Click to view web link

Abstract : Universiti Pendidikan Sultan Idris

The Coronavirus disease 2019, or COVID-19, has shifted the medical paradigm from face-to-face to telehealth. Telehealth has become a vital resource to contain the virus spread and ensure the continued care of patients. In terms of preventing cardiovascular diseases, automating electrocardiogram (ECG) classification is a promising telehealth intervention. The healthcare service ensures that patient care is appropriate, comfortable, and accessible. Convolutional neural networks (CNNs) have demonstrated promising results in ECG categorization, which require high accuracy and short training time to ensure healthcare quality. This study proposes a one-dimensional-CNN (1D-CNN) arrhythmia classification based on the differential evolution (DE) algorithm to optimize the accuracy of ECG classification and training time. The performance of 1D-CNNs of different activation functions are optimized based on the standard DE algorithm. Finally, based on MIT-BIH and SCDH arrhythmia databases, the performances of optimized and unoptimized 1D-CNN are compared and analysed. Results show that the 1D-CNN optimized by the DE has higher accuracy in heartbeats classification. The optimized 1D-CNN improves from 97.6% to 99.5% on MIT-BIH and from 80.2% to 88.5% on SCDH. Therefore, the optimized 1D-CNN shows improvements of 1.9% and 8.3% in the two datasets, respectively. In addition, compared with the unoptimized 1D-CNN based on the same parameter settings, the optimized 1D-CNN has less training time. Under the conditions of ReLU function and 10 epochs, the training takes 9.22s on MIT-BIH and 10.35s on SCDH, reducing training time by 67.2% and 64.2%, respectively. 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

References

Acharya UR et al (2017) A deep convolutional neural network model to classify heartbeats. Comput Biol Med 89:389–396. https://doi.org/10.1016/j.compbiomed.2017.08.022

Aghamaleki JA, AshkaniChenarlogh V (2019) Multi-stream CNN for facial expression recognition in limited training data. Multimed Tools Appl 78(16):22861–22882. https://doi.org/10.1007/s11042-019-7530-7

Bhagyalakshmi V, Pujeri RV, Devanagavi GD (2021) GB-SVNN: Genetic BAT assisted support vector neural network for arrhythmia classifcation using ECG signals. J King Saud Univ Inf Sci 33(1):54–67. https://doi.org/10.1016/j.jksuci.2018.02.005

Chandra BS, Sastry CS, Jana S (2019) Robust Heartbeat Detection from Multimodal Data via CNN-Based Generalizable Information Fusion. IEEE Trans Biomed Eng 66(3):710–717. https://doi.org/10.1109/TBME.2018.2854899

Degirmenci M, Ozdemir MA, Izci E, Akan A (2022) Arrhythmic heartbeat classifcation using 2d convolutional neural networks. Irbm 43(5):422–433

Diker A, Sönmez Y, Özyurt F, Avcı E, Avcı D (2021) Examination of the ECG signal classifcation technique DEA-ELM using deep convolutional neural network features. Multimed Tools Appl 80(16):24777–24800. https://doi.org/10.1007/s11042-021-10517-8

Ding XYYQF (2017) Research survey of diferential evolution algorithms. CAAI Trans Intell Syst 12:431–442

El_Rahman SA (2019) Biometric human recognition system based on ECG. Multimed Tools Appl. 78(13):17555-17572, https://doi.org/10.1007/s11042-019-7152-0

Erdenebayar U, Kim H, Park JU, Kang D, Lee KJ (2019) Automatic prediction of atrial fbrillation based on convolutional neural network using a short-term normal electrocardiogram signal. J Korean Med Sci 34(7):1–10. https://doi.org/10.3346/jkms.2019.34.e64

Escalona-Morán MA, Soriano MC, Fischer I, Mirasso CR (2015) Electrocardiogram classifcation using reservoir computing with logistic regression. IEEE J Biomed Heal Inform 19(3):892–898. https://doi.org/10.1109/JBHI.2014.2332001

Fan X, Yao Q, Cai Y, Miao F, Sun F, Li Y (2018) Multiscaled Fusion of Deep Convolutional Neural Networks for Screening Atrial Fibrillation from Single Lead Short ECG Recordings. IEEE J Biomed Heal Inform 22(6):1744–1753. https://doi.org/10.1109/JBHI.2018.2858789

Goldberger AL et al. (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals, Circulation, 101(23), 10.1161/01.cir.101.23.e215

González-Lozoya SM, de la Calleja J, Pellegrin L, Escalante HJ, Medina MA, Benitez-Ruiz A (2020) Recognition of facial expressions based on CNN features. Multimed Tools Appl 79(19–20):13987–14007. https://doi.org/10.1007/s11042-020-08681-4

Hadi SJ, Tombul M, Salih SQ, Al-Ansari N, Yaseen ZM (2020) The Capacity of the Hybridizing Wavelet Transformation Approach with Data-Driven Models for Modeling Monthly-Scale Streamfow. IEEE Access 8:101993–102006. https://doi.org/10.1109/ACCESS.2020.2998437

Hammad M, Luo G, and Wang K (2019) Cancelable biometric authentication system based on ECG, 78(2). Multimedia Tools and Applications, https://doi.org/10.1007/s11042-021-10517-8

Khairandish MO, Sharma M, Jain V, Chatterjee JM, and Jhanjhi NZ (2021) A hybrid CNN-SVM threshold segmentation approach for tumor detection and classifcation of MRI brain images, IRBM, https://doi.org/10.1016/j.irbm.2021.06.003

Leon M and Xiong N (2016) Adapting diferential evolution algorithms for continuous optimization via greedy adjustment of control parameters, J Artif Intell soft Comput Res, 6, https://doi.org/10.1515/jaiscr-2016-0009

Liu T, Si Y, Wen D, Zang M, Lang L (2016) Dictionary learning for VQ feature extraction in ECG beats classifcation. Expert Syst Appl 53:129–137. https://doi.org/10.1016/j.eswa.2016.01.031

Ma Y, Liu Y, Xie Q, Li L (2019) CNN-feature based automatic image annotation method. Multimed Tools Appl 78(3):3767–3780. https://doi.org/10.1007/s11042-018-6038-x

Pant M, Zaheer H, Garcia-Hernandez L, Abraham A (2020) Diferential Evolution: A review of more than two decades of research. Eng Appl Artif Intell 90:103479. https://doi.org/10.1016/j.engappai.2020.103479

Sadrawi M et al (2017) Arrhythmia evaluation in wearable ECG devices. Sensors (Switzerland) 17(11):1–14. https://doi.org/10.3390/s17112445

Sahoo S, Kanungo B, Behera S, Sabut S (2017) Multiresolution wavelet transform based feature extraction and ECG classifcation to detect cardiac abnormalities. Meas J Int Meas Confed 108:55–66. https://doi.org/10.1016/j.measurement.2017.05.022

Salem M, Taheri S, Yuan JS (2018) "ECG Arrhythmia Classifcation Using Transfer Learning from 2- Dimensional Deep CNN Features, 2018 IEEE Biomed Circuits Syst Conf BioCAS 2018 - Proc., 1–4, https://doi.org/10.1109/BIOCAS.2018.8584808

Sánchez-Reolid R, de la Rosa FL, López MT, Fernández-Caballero A (2022) One-dimensional convolutional neural networks for low/high arousal classifcation from electrodermal activity. Biomed Signal Process Control 71:103203. https://doi.org/10.1016/j.bspc.2021.103203

Shepoval’nikov RA, Nemirko AP, Kalinichenko AN, Abramchenko VV (2006) Investigation of time, amplitude, and frequency parameters of a direct fetal ECG signal during labor and delivery. Pattern Recognit Image Anal 16(1):74–76. https://doi.org/10.1134/S1054661806010238

This material may be protected under Copyright Act which governs the making of photocopies or reproductions of copyrighted materials.
You may use the digitized material for private study, scholarship, or research.

Back to previous page