An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks

Many algorithms have been developed for automated electrocardiogram (ECG) classification. Due to the non-stationary nature of the ECG signal, it is rather challenging to use traditional handcraft methods, such as time-based analysis of feature extraction and classification, to pave the way for machi...

Full description

Bibliographic Details
Main Authors:	Ihsanto, Eko, Ramli, Kalamullah, Sudiana, Dodi, Gunawan, Teddy Surya
Format:	Article
Language:	English
Published:	MDPI 2020
Subjects:	TK7885 Computer engineering
Online Access:	http://irep.iium.edu.my/78347/ http://irep.iium.edu.my/78347/ http://irep.iium.edu.my/78347/ http://irep.iium.edu.my/78347/1/78347_An%20Efficient%20Algorithm%20for%20Cardiac%20Arrhythmia.pdf

id	iium-78347
recordtype	eprints
spelling	iium-783472020-02-05T00:46:50Z http://irep.iium.edu.my/78347/ An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks Ihsanto, Eko Ramli, Kalamullah Sudiana, Dodi Gunawan, Teddy Surya TK7885 Computer engineering Many algorithms have been developed for automated electrocardiogram (ECG) classification. Due to the non-stationary nature of the ECG signal, it is rather challenging to use traditional handcraft methods, such as time-based analysis of feature extraction and classification, to pave the way for machine learning implementation. This paper proposed a novel method, i.e., the ensemble of depthwise separable convolutional (DSC) neural networks for the classification of cardiac arrhythmia ECG beats. Using our proposed method, the four stages of ECG classification, i.e., QRS detection, preprocessing, feature extraction, and classification, were reduced to two steps only, i.e., QRS detection and classification. No preprocessing method was required while feature extraction was combined with classification. Moreover, to reduce the computational cost while maintaining its accuracy, several techniques were implemented, including All Convolutional Network (ACN), Batch Normalization (BN), and ensemble convolutional neural networks. The performance of the proposed ensemble CNNs were evaluated using the MIT-BIH arrythmia database. In the training phase, around 22% of the 110,057 beats data extracted from 48 records were utilized. Using only these 22% labeled training data, our proposed algorithm was able to classify the remaining 78% of the database into 16 classes. Furthermore, the sensitivity ( Sn ), specificity ( Sp ), and positive predictivity ( Pp ), and accuracy ( Acc ) are 99.03%, 99.94%, 99.03%, and 99.88%, respectively. The proposed algorithm required around 180 μs, which is suitable for real time application. These results showed that our proposed method outperformed other state of the art methods. MDPI 2020-01-09 Article PeerReviewed application/pdf en http://irep.iium.edu.my/78347/1/78347_An%20Efficient%20Algorithm%20for%20Cardiac%20Arrhythmia.pdf Ihsanto, Eko and Ramli, Kalamullah and Sudiana, Dodi and Gunawan, Teddy Surya (2020) An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks. Applied Sciences, 10 (2). pp. 483-499. E-ISSN 2076-3417 https://www.mdpi.com/2076-3417/10/2/483/htm https://doi.org/10.3390/app10020483
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	TK7885 Computer engineering
spellingShingle	TK7885 Computer engineering Ihsanto, Eko Ramli, Kalamullah Sudiana, Dodi Gunawan, Teddy Surya An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks
description	Many algorithms have been developed for automated electrocardiogram (ECG) classification. Due to the non-stationary nature of the ECG signal, it is rather challenging to use traditional handcraft methods, such as time-based analysis of feature extraction and classification, to pave the way for machine learning implementation. This paper proposed a novel method, i.e., the ensemble of depthwise separable convolutional (DSC) neural networks for the classification of cardiac arrhythmia ECG beats. Using our proposed method, the four stages of ECG classification, i.e., QRS detection, preprocessing, feature extraction, and classification, were reduced to two steps only, i.e., QRS detection and classification. No preprocessing method was required while feature extraction was combined with classification. Moreover, to reduce the computational cost while maintaining its accuracy, several techniques were implemented, including All Convolutional Network (ACN), Batch Normalization (BN), and ensemble convolutional neural networks. The performance of the proposed ensemble CNNs were evaluated using the MIT-BIH arrythmia database. In the training phase, around 22% of the 110,057 beats data extracted from 48 records were utilized. Using only these 22% labeled training data, our proposed algorithm was able to classify the remaining 78% of the database into 16 classes. Furthermore, the sensitivity ( Sn ), specificity ( Sp ), and positive predictivity ( Pp ), and accuracy ( Acc ) are 99.03%, 99.94%, 99.03%, and 99.88%, respectively. The proposed algorithm required around 180 μs, which is suitable for real time application. These results showed that our proposed method outperformed other state of the art methods.
format	Article
author	Ihsanto, Eko Ramli, Kalamullah Sudiana, Dodi Gunawan, Teddy Surya
author_facet	Ihsanto, Eko Ramli, Kalamullah Sudiana, Dodi Gunawan, Teddy Surya
author_sort	Ihsanto, Eko
title	An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks
title_short	An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks
title_full	An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks
title_fullStr	An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks
title_full_unstemmed	An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks
title_sort	efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise separable convolutional neural networks
publisher	MDPI
publishDate	2020
url	http://irep.iium.edu.my/78347/ http://irep.iium.edu.my/78347/ http://irep.iium.edu.my/78347/ http://irep.iium.edu.my/78347/1/78347_An%20Efficient%20Algorithm%20for%20Cardiac%20Arrhythmia.pdf
first_indexed	2023-09-18T21:50:24Z
last_indexed	2023-09-18T21:50:24Z
_version_	1777413730982690816

An efficient algorithm for cardiac arrhythmia classification using ensemble of depthwise Separable convolutional neural networks

Similar Items