Generating X-Ray images of covid-19 using generative adversarial networks (Gans) and covid-19 detection using convolutional neural natworks (CNN)
dc.contributor.author | Ayed Nacereddine | |
dc.contributor.author | Aggoun Mohammed Amin | |
dc.contributor.author | Zouad Sara | |
dc.date.accessioned | 2021-11-06T07:52:52Z | |
dc.date.available | 2021-11-06T07:52:52Z | |
dc.date.issued | 2021 | |
dc.description.abstract | Recently, the generative approach becomes one of the most important areas of deep learning. Deep learning, and generative adversarial networks are the new line of research in this field, GANs have proved their ability to generate high-resolution images and achieved great success in computer vision. We suppose that this tool will be able to generate new accurate images for the COVID-19 dataset to improve the diagnosis of the disease. The expected benefit of this work is to create a perception using deep convolutional generative adversarial networks (DCGANs) and convolutional neural networks (CNN), to explore the potential of this powerful deep learning tool to serve COVID-19 diagnosis. As an impact for further studies in the future, this work may offer insights on how to generate new images to help diagnose many diseases. | ar |
dc.identifier.uri | http://hdl.handle.net/123456789/11169 | |
dc.language.iso | en | ar |
dc.publisher | Université de Larbi Ben M’hidi-Oum Oum El Bouaghi | ar |
dc.subject | Deep learning | ar |
dc.subject | The generative approach | ar |
dc.subject | Generative adversarial networks | ar |
dc.title | Generating X-Ray images of covid-19 using generative adversarial networks (Gans) and covid-19 detection using convolutional neural natworks (CNN) | ar |
dc.type | Other | ar |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- memoire aggoun et ayed.pdf
- Size:
- 5.22 MB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: