An Advanced Study on the Recognition of Coronavirus Disease (COVID-19) Using Deep Learning Network

Abstract

A new virus disease spread last December in Wuhan city in China for uncertain reasons and it was named by the World Health Organization (WHO) as COVID-19.  The Coronavirus disease (COVID-19) has had an incredible influence in the last few years. It causes thousands of deaths around the world. This makes a rapid research movement to deal with this new virus. As a computer science, much technical research has been done to tackle it by using image processing algorithms. This study was conducted by experimenting on the recent dataset, the Kaggle dataset of COVID-19 X-ray images, and used the ResNet50 deep learning network with 5 and 10-fold cross-validation. This study introduces a method based on deep learning networks to classify COVID-19 based on X-ray images. This result is encouraging to rely on to classify the infected people from the normal. The experiment results show that 5 folds give more effective results than 10 folds with an accuracy rate of 97.28%. Henceforth, deep learning can offer significant results in recognizing the virus in its earliest stages. Future studies can be conducted on different architectures of deep learning using different datasets which helps to recognize the infected people in earlier stages and save their lives.