- Alzahraa Elsayed
Systems and Computers Engineering Dept., Faculty of Engineering, Al-Azhar University, Nasr city 11765, Cairo, Egypt.
alzahraa.salah@azhar.edu.eg
ISSN: 2182-2069 (printed) / ISSN: 2182-2077 (online)
COVID-19 Detection Based on Fog-Cloud Framework Using Deep Learning
According to the World Health Organization (WHO), the coronavirus disease 2019 (COVID-19) is considered as a pandemic disease. Therefore, several studies were carried out to identify COVID-19 using various strategies with small datasets. Where, most of cloud-based healthcare services are based on a centralized transmission procedure for huge amounts of information with high speed. Therefore, in this paper, we present a framework based on fog-cloud computing architecture for COVID -19 for diagnosis this disease with high speed. Moreover, we implemented a modified Convolutional Neural Network (CNN) on a fog computing layer to detect COVID-19 from chest X-ray (CXR) images. In addition, we measured the performance accuracy of the proposed model in three stages. In the first, the proposed model experimented with using two layers of CNN and the results showed that the training and validation accuracy gradually increased to 99.87% and 95.50% respectively. In the second, the proposed model experimented using three layers of CNN and the results showed that the training and validation accuracy increased to 99.88% and 96.50% respectively. Finally, we compared our proposed model with other studies and with three pre-trained models (VGG16, VGG19 and MobileNet).So, the comparison showed that the accuracy of our proposed model is higher than others by 99.88% in classifying COVID-19, and normal cases with 99.88% accuracy, 96.5% validation rate, 100% of precession, 100% of recall and 100% of F1 Score.