Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JIKSI (Jurnal Ilmu Komputer dan Sistem Informasi)
Jourdan Stanley
Unknown Affiliation
Computer Science & IT Mathematics Other

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Sistem Pengenalan Covid-19 Berdasarkan Foto X-ray Paru dengan Metode EfficientNet-B0 Jourdan Stanley; Chairisni Lubis; Teny Handhayani
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 10 No. 2 (2022): JURNAL ILMU KOMPUTER DAN SISTEM INFORMASI
Publisher : Fakultas Teknologi Informasi Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/jiksi.v10i2.22549

Abstract

Covid-19 is a viral infection disease severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), Covid-19 is a group of viruses that attack the respiratory system in humans which can cause symptoms ranging from mild symptoms to severe symptoms. Currently, to detect whether a person is infected with the Covid-19 virus or not, several tests can be carried out, one of which is the polymerse chain reaction (PCR) examination. This type of examination has a high level of accuracy but this examination requires quite expensive costs, adequate laboratories and requires a long time. So from these problems there is another alternative, namely radiological examination. From these problems, a system was built that can perform classification based on x-ray images of the lungs using the convolutional neural network (CNN) method of Efficientnet-B0 architecture. This system is expected to assist medical personnel in pre-diagnosing a patient's lung condition based on their lung x-ray without changing the role of the medical personnel. After successfully building a Covid-19 recognition system, the system will be tested using the confusion matrix method where in this test there are 2 scenarios. In the first scenario, the data trained using the CLAHE preprocessing method obtained an accuracy rate of 98%, while in the second scenario the data was trained without using the CLAHE preprocessing method, the results obtained an accuracy rate of 97%. Previous research was conducted using the resnet-18 method and obtained an accuracy rate of 92%. From the results obtained prove that Efficientnet is able to increase the level of accuracy from previous studies.
Co-Authors Chairisni Lubis Teny Handhayani