Detection of COVID-19 chest x-ray using support vector machine and convolutional neural network

Dian Candra Rini Novitasari; Rimuljo Hendradi; Rezzy Eko Caraka; Yuanita Rachmawati; Nurul Zainal Fanani; Anang Syarifudin; Toni Toharudin; Rung Ching Chen

doi:10.28919/cmbn/4765

Detection of COVID-19 chest x-ray using support vector machine and convolutional neural network

Dian Candra Rini Novitasari, Rimuljo Hendradi, Rezzy Eko Caraka, Yuanita Rachmawati, Nurul Zainal Fanani, Anang Syarifudin, Toni Toharudin, Rung Ching Chen

Research output: Contribution to journal › Article › peer-review

41 Citations (Scopus)

Abstract

This study aims to detect whether patients examined are healthy, Coronavirus positive, or just have pneumonia based on chest X-ray data using Convolutional Neural Network method as feature extraction and Support Vector Machine as a classification method or called Convolutional Support Vector Machine. Experiments carried out were comparing the kernel used, feature selection methods, architecture in feature extraction, and separated classes. Our instrument reached the accuracy of 97.33% in the separation of 3 classes (normal, pneumonia, COVID19) and 100% in the separation of 2 classes, that is (normal, COVID19) and (pneumonia, COVID19), respectively. Based on these results, it can be concluded that the feature selection method can improve gained accuracy ±98%.

Original language	English
Article number	42
Pages (from-to)	1-19
Number of pages	19
Journal	Communications in Mathematical Biology and Neuroscience
Volume	2020
DOIs	https://doi.org/10.28919/cmbn/4765
Publication status	Published - 2020

Keywords

COVID-19
Convolution
GoogleNet
Resnet
SVM

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.28919/cmbn/4765

Cite this

@article{859290b88af84681bcba1117305b86b7,

title = "Detection of COVID-19 chest x-ray using support vector machine and convolutional neural network",

abstract = "This study aims to detect whether patients examined are healthy, Coronavirus positive, or just have pneumonia based on chest X-ray data using Convolutional Neural Network method as feature extraction and Support Vector Machine as a classification method or called Convolutional Support Vector Machine. Experiments carried out were comparing the kernel used, feature selection methods, architecture in feature extraction, and separated classes. Our instrument reached the accuracy of 97.33% in the separation of 3 classes (normal, pneumonia, COVID19) and 100% in the separation of 2 classes, that is (normal, COVID19) and (pneumonia, COVID19), respectively. Based on these results, it can be concluded that the feature selection method can improve gained accuracy ±98%.",

keywords = "COVID-19, Convolution, GoogleNet, Resnet, SVM",

author = "Novitasari, {Dian Candra Rini} and Rimuljo Hendradi and Caraka, {Rezzy Eko} and Yuanita Rachmawati and Fanani, {Nurul Zainal} and Anang Syarifudin and Toni Toharudin and Chen, {Rung Ching}",

note = "Publisher Copyright: {\textcopyright} 2020 the author(s).",

year = "2020",

doi = "10.28919/cmbn/4765",

language = "English",

volume = "2020",

pages = "1--19",

journal = "Communications in Mathematical Biology and Neuroscience",

issn = "2052-2541",

publisher = "SCIK Publishing Corporation",

}

TY - JOUR

T1 - Detection of COVID-19 chest x-ray using support vector machine and convolutional neural network

AU - Novitasari, Dian Candra Rini

AU - Hendradi, Rimuljo

AU - Caraka, Rezzy Eko

AU - Rachmawati, Yuanita

AU - Fanani, Nurul Zainal

AU - Syarifudin, Anang

AU - Toharudin, Toni

AU - Chen, Rung Ching

PY - 2020

Y1 - 2020

N2 - This study aims to detect whether patients examined are healthy, Coronavirus positive, or just have pneumonia based on chest X-ray data using Convolutional Neural Network method as feature extraction and Support Vector Machine as a classification method or called Convolutional Support Vector Machine. Experiments carried out were comparing the kernel used, feature selection methods, architecture in feature extraction, and separated classes. Our instrument reached the accuracy of 97.33% in the separation of 3 classes (normal, pneumonia, COVID19) and 100% in the separation of 2 classes, that is (normal, COVID19) and (pneumonia, COVID19), respectively. Based on these results, it can be concluded that the feature selection method can improve gained accuracy ±98%.

AB - This study aims to detect whether patients examined are healthy, Coronavirus positive, or just have pneumonia based on chest X-ray data using Convolutional Neural Network method as feature extraction and Support Vector Machine as a classification method or called Convolutional Support Vector Machine. Experiments carried out were comparing the kernel used, feature selection methods, architecture in feature extraction, and separated classes. Our instrument reached the accuracy of 97.33% in the separation of 3 classes (normal, pneumonia, COVID19) and 100% in the separation of 2 classes, that is (normal, COVID19) and (pneumonia, COVID19), respectively. Based on these results, it can be concluded that the feature selection method can improve gained accuracy ±98%.

KW - COVID-19

KW - Convolution

KW - GoogleNet

KW - Resnet

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=85088322657&partnerID=8YFLogxK

U2 - 10.28919/cmbn/4765

DO - 10.28919/cmbn/4765

M3 - Article

AN - SCOPUS:85088322657

SN - 2052-2541

VL - 2020

SP - 1

EP - 19

JO - Communications in Mathematical Biology and Neuroscience

JF - Communications in Mathematical Biology and Neuroscience

M1 - 42

ER -

Detection of COVID-19 chest x-ray using support vector machine and convolutional neural network

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this