Design a simple Covid-19 detection using corodet: A deep learning-based classification
COVID-19 is an infectious disease caused by the coronavirus that causes acute pneumonia where the symptoms are influenced by the immune system. The information was that this virus was first discovered in the city of Wuhan, China in December 2019, then spread quickly to almost all over the world. For...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Tagungsbericht |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | COVID-19 is an infectious disease caused by the coronavirus that causes acute pneumonia where the symptoms are influenced by the immune system. The information was that this virus was first discovered in the city of Wuhan, China in December 2019, then spread quickly to almost all over the world. For example, in Indonesia, Covid-19 cases have reached 2 million cases, with 1.8 million recovered cases and 55 thousand deaths, so that it has a severe impact in all sectors, especially health. This is exacerbated by the presence of a new variant of the coronavirus, which transmission and spread are quite fast. A need for a testing kit for COVID-19 is crucial because using the conventional method takes more time. So we like to propose a simple covid-19 detection using a deep learning-based classification. After a literature study and comparing three models Ozturk, CoroNet, and CoroDet, we get that CoroDet Model has the best performance in accuracy to detect COVID-19. Corodet has been tested using chest X-ray and CT images and providing accurate diagnostics for 2 class classifications (COVID and normal) 99.1%, 3 class classifications (COVID, normal, and pneumonia) 94.2%, and 4 class classification (COVID, normal, non-COVID viral pneumonia, and non-COVID bacterial pneumonia) 91.2%. |
---|---|
ISSN: | 0094-243X 1551-7616 |
DOI: | 10.1063/5.0110764 |