Klasifikasi K-NN dalam Identifikasi Penyakit COVID-19 Menggunakan Ekstraksi Fitur GLCM

JOURNAL OF APPLIED INFORMATICS AND COMPUTING

View Publication Info
 
 
Field Value
 
Title Klasifikasi K-NN dalam Identifikasi Penyakit COVID-19 Menggunakan Ekstraksi Fitur GLCM
 
Creator Nafisah, Nisa
Adam, Riza Ibnu
Carudin, Carudin
 
Description Covid-19 is a disease that is endemic in various parts of the world including Indonesia, this disease infects the respiratory tract caused by a new type of corona virus. To find out the presence of this virus in the body, medical examinations such as blood tests, radiological examinations can be carried out X-rays (x-rays) and swabs. Therefore, in this study, identification covid-19 disease based on the rongen image from which the image was extracted using the GLCM feature extraction method, namely contrast, correlation, energy, and homogeneity, after obtaining the value from the extraction and then classified using data mining classification method, namely k-nearest neighbor by doing 3 modeling the input value of k. The results obtained from the classification obtained an accuracy of 80% in model 3 with a value of k = 5 and in models 1 and 2 obtained an accuracy of 90% with a value of k = 1 and k = 3.
Covid-19 merupakan penyakit yang sedang mewabah diberbagai belahan duni ae trmasuk Indonesia, penyakit ini menginfeksi saluran pernapasan yang disebabkan  oleh jenis virus corona baru. Untuk mengetahui adanya virus ini diddalam tubuh  dapat dilakukan pemeriksaan medis seperti cek darah, pemeriksaan radiologi  rontgent (x-ray) dan swab. Oleh karena itu pda penelitian ini dilakukan identifikasi  penyakit covid-19 berdasarkan citra rongen yang mana citra tersebut di ekstraksi  menggunakan metode fitur ekstraksi GLCM yaitu contrast, correlation, energy, dan  homogeneity, setelah didapat nilai dari ekstraksi lalu di klasifikasikan menggunakan metode klasifikasi data mining yaitu k-nearest neighbor dengan melakukan 3  pemodelan nilai inputan k. hasil yan diperoleh dari pengklasifikasian didapat akurasi  sebesar 80%pada model 3 dengan nilai k = 5 dan pada model 1 dan 2 diperoleh hasil  akurasi sebesar 90% dengan niali k = 1 dan k = 3. 
 
Publisher Politeknik Negeri Batam
 
Date 2021-10-22
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
 
Format application/pdf
 
Identifier https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/3258
10.30871/jaic.v5i2.3258
 
Source Journal of Applied Informatics and Computing (JAIC); Vol 5 No 2 (2021): Desember 2021; 128-132
Journal of Applied Informatics and Computing (JAIC); Vol 5 No 2 (2021): Desember 2021; 128-132
2548-6861
10.30871/jaic.v5i2
 
Language eng
 
Relation https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/3258/1501
 
Rights Copyright (c) 2021 Nisa Nafisah, Riza Ibnu Adam, Carudin Carudin
http://creativecommons.org/licenses/by-sa/4.0
 

Contact Us

The PKP Index is an initiative of the Public Knowledge Project.

For PKP Publishing Services please use the PKP|PS contact form.

For support with PKP software we encourage users to consult our wiki for documentation and search our support forums.

For any other correspondence feel free to contact us using the PKP contact form.

Find Us

Twitter

Copyright © 2015-2018 Simon Fraser University Library