COVID-19IraqKirkukDataset: Development and evaluation of an Iraqi dataset for COVID-19 classification based on deep learning
نویسندگان
1 Computer Science Department, College of Computer Science and Information Technology, Kirkuk University, Kirkuk, Iraq
2 Software Department, College of Computer Science and Information Technology, Kirkuk University, Kirkuk, Iraq
doi
10.22075/ijnaa.2023.7317چکیده
In the last two years, the coronavirus (COVID-19) pandemic put healthcare systems around the world under tremendous pressure. There have been intelligent systems (Machine Learning (ML) and Deep Learning (DL)) able to identify COVID-19 from similar normal diseases. The algorithms use Imaging techniques (like Chest X-Rays) in classifying COVID-19. Therefore, many global COVID-19 datasets have been released. However, so far, no public local Iraqi dataset has been developed. Therefore, our contribution is two folds. First, we investigate the techniques of deep learning techniques in COVID-19 classification. Second, we develop a new COVID-19 dataset, namely, “Covid-19IraqKirkukDataset” collected from hospitals in Kirkuk, Iraq. To the best of our knowledge, our dataset is the first COVID-19 dataset. Then, the evaluation of Covid19IraqKirkukDataset using Convolutional Neural Networks (CNNs) demonstrates promising classification outcomes.
