Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JNANALOKA
Visq Delica
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Engineering Industrial & Manufacturing Engineering Mechanical Engineering Social Sciences Transportation Other

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

Found 1 Documents
Search

 1 
Penerapan transfer learning pada convolutional neural networks dalam deteksi covid-19. Buyut Khoirul Umri; Visq Delica
JNANALOKA Vol. 02 No. 02 September Tahun 2021
Publisher : Lentera Dua Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36802/jnanaloka.2021.v2-no2-53-61

Abstract

The Covid-19 pandemic has become a serious problem in the world, including Indonesia, until now, the virus that emerged at the end of 2019 is still a serious problem. The number of cases of infected people continues to increase and reaches more than two hundred million cases worldwide. To carry out this rapid test, it did not run smoothly but experienced many obstacles experienced by the Medical team, one of which was the limitation of the Covid-19 test kit, so scientists took other diagnostic steps. In the field of informatics, scientists use several diagnoses, one of which is X-ray images of the lungs. CXR images are currently often used for the detection process using the CNN algorithm. This research uses transfer learning method which will be tested in large and small scale datasets. The best result of all the models tested is MobileNet with an accuracy of 98.11% which was tested on a large-scale dataset and the lowest was obtained by ResNet50 which was tested on a small-scale dataset with an accuracy of 41.94%. The large-scale dataset also shows improved accuracy across all tested transfer learning models.
Co-Authors Buyut Khoirul Umri