WITHDRAWN: Overview of deep learning models for identification Covid-19
| Autor: | Hanaa Mohsin Ahmed, Basma Wael Abdullah |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
010302 applied physics
2019-20 coronavirus outbreak Diagnostic methods Coronavirus disease 2019 (COVID-19) Computer science business.industry Deep learning Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) 02 engineering and technology 021001 nanoscience & nanotechnology Machine learning computer.software_genre 01 natural sciences Identification (information) Global population 0103 physical sciences Pandemic Artificial intelligence 0210 nano-technology business computer |
| Zdroj: | Materials Today: Proceedings. |
| ISSN: | 2214-7853 |
| DOI: | 10.1016/j.matpr.2021.05.553 |
| Popis: | The well-being and health of global population is continuously and badly affected by COVID-19 pandemic. Thus, to prevent the spread the pandemic between individuals, there is high importance in implementing automatic detection systems as rapid alternative diagnosis. The virus is affecting the person's respiratory system as well as creating white patchy shadows in the X-ray images of the lungs of individuals experiencing COVID-19. Also, deep learning can be defined as a useful and efficient AI technique used for analyzing chest X-ray images for reliable and effective screening of COVID-19; therefore, distinguishing people infected with COVID-19 and normal persons, and after that the infected individuals will be isolated for mitigating the virus spread. This study provides an overview regarding a few of the modern deep learning-based COVID-19, with design steps and types, also it compares the diagnostic method of COVID-19 with other methods of deep learning created with the use of radiology images. After a comparison between the most recent methods used in the previous works, it was found that RestNet50 pre-trained and DCNN model gives accuracy of 98%, which is the highest reported so far from among other proposed models were discussed in this paper. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect