Home > Research > Publications & Outputs > Classification of arrhythmia by using deep lear...

Text available via DOI:

View graph of relations

Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation. / Ullah, Amin; Anwar, Syed Muhammad; Bilal, Muhammad et al.
In: Remote Sensing, Vol. 12, No. 10, 1685, 01.05.2020.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Ullah A, Anwar SM, Bilal M, Mehmood RM. Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation. Remote Sensing. 2020 May 1;12(10):1685. doi: 10.3390/rs12101685

Author

Ullah, Amin ; Anwar, Syed Muhammad ; Bilal, Muhammad et al. / Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation. In: Remote Sensing. 2020 ; Vol. 12, No. 10.

Bibtex

@article{6c4e7f1e11e0452388bbd0d0bf10aa4f,
title = "Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation",
abstract = "The electrocardiogram (ECG) is one of the most extensively employed signals used in the diagnosis and prediction of cardiovascular diseases (CVDs). The ECG signals can capture the heart's rhythmic irregularities, commonly known as arrhythmias. A careful study of ECG signals is crucial for precise diagnoses of patients' acute and chronic heart conditions. In this study, we propose a two-dimensional (2-D) convolutional neural network (CNN) model for the classification of ECG signals into eight classes; namely, normal beat, premature ventricular contraction beat, paced beat, right bundle branch block beat, left bundle branch block beat, atrial premature contraction beat, ventricular flutter wave beat, and ventricular escape beat. The one-dimensional ECG time series signals are transformed into 2-D spectrograms through short-time Fourier transform. The 2-D CNN model consisting of four convolutional layers and four pooling layers is designed for extracting robust features from the input spectrograms. Our proposed methodology is evaluated on a publicly available MIT-BIH arrhythmia dataset. We achieved a state-of-the-art average classification accuracy of 99.11%, which is better than those of recently reported results in classifying similar types of arrhythmias. The performance is significant in other indices as well, including sensitivity and specificity, which indicates the success of the proposed method.",
keywords = "Arrhythmia, Classification, Convolution neural network, Deep learning, ECG signal",
author = "Amin Ullah and Anwar, {Syed Muhammad} and Muhammad Bilal and Mehmood, {Raja Majid}",
year = "2020",
month = may,
day = "1",
doi = "10.3390/rs12101685",
language = "English",
volume = "12",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "MDPI AG",
number = "10",

}

RIS

TY - JOUR

T1 - Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation

AU - Ullah, Amin

AU - Anwar, Syed Muhammad

AU - Bilal, Muhammad

AU - Mehmood, Raja Majid

PY - 2020/5/1

Y1 - 2020/5/1

N2 - The electrocardiogram (ECG) is one of the most extensively employed signals used in the diagnosis and prediction of cardiovascular diseases (CVDs). The ECG signals can capture the heart's rhythmic irregularities, commonly known as arrhythmias. A careful study of ECG signals is crucial for precise diagnoses of patients' acute and chronic heart conditions. In this study, we propose a two-dimensional (2-D) convolutional neural network (CNN) model for the classification of ECG signals into eight classes; namely, normal beat, premature ventricular contraction beat, paced beat, right bundle branch block beat, left bundle branch block beat, atrial premature contraction beat, ventricular flutter wave beat, and ventricular escape beat. The one-dimensional ECG time series signals are transformed into 2-D spectrograms through short-time Fourier transform. The 2-D CNN model consisting of four convolutional layers and four pooling layers is designed for extracting robust features from the input spectrograms. Our proposed methodology is evaluated on a publicly available MIT-BIH arrhythmia dataset. We achieved a state-of-the-art average classification accuracy of 99.11%, which is better than those of recently reported results in classifying similar types of arrhythmias. The performance is significant in other indices as well, including sensitivity and specificity, which indicates the success of the proposed method.

AB - The electrocardiogram (ECG) is one of the most extensively employed signals used in the diagnosis and prediction of cardiovascular diseases (CVDs). The ECG signals can capture the heart's rhythmic irregularities, commonly known as arrhythmias. A careful study of ECG signals is crucial for precise diagnoses of patients' acute and chronic heart conditions. In this study, we propose a two-dimensional (2-D) convolutional neural network (CNN) model for the classification of ECG signals into eight classes; namely, normal beat, premature ventricular contraction beat, paced beat, right bundle branch block beat, left bundle branch block beat, atrial premature contraction beat, ventricular flutter wave beat, and ventricular escape beat. The one-dimensional ECG time series signals are transformed into 2-D spectrograms through short-time Fourier transform. The 2-D CNN model consisting of four convolutional layers and four pooling layers is designed for extracting robust features from the input spectrograms. Our proposed methodology is evaluated on a publicly available MIT-BIH arrhythmia dataset. We achieved a state-of-the-art average classification accuracy of 99.11%, which is better than those of recently reported results in classifying similar types of arrhythmias. The performance is significant in other indices as well, including sensitivity and specificity, which indicates the success of the proposed method.

KW - Arrhythmia

KW - Classification

KW - Convolution neural network

KW - Deep learning

KW - ECG signal

UR - http://www.scopus.com/inward/record.url?scp=85085571762&partnerID=8YFLogxK

U2 - 10.3390/rs12101685

DO - 10.3390/rs12101685

M3 - Journal article

AN - SCOPUS:85085571762

VL - 12

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 10

M1 - 1685

ER -