An H(2)O’s Deep Learning-Inspired Model Based on Big Data Analytics for Coronavirus Disease (COVID-19) Diagnosis

Elghamrawy, Sally

The outbreak of coronavirus diseases (COVID-19) has rabidly spread all over the world. The World Health Organization (WHO) has announced that coronavirus COVID-19 is an international pandemic. Big Data analytics tools must handle and analyse the massive amount of big medical data, generated daily, quickly due to the fact that time is very significant issue in healthcare applications. In addition, several deep learning algorithms are used along with big data analysis processes to help in detecting COVID-19 outbreaks and predicting their worldwide spread. Many researchers developed their models to diagnosis COVID-19 using Computed Tomography (CT) or X-ray imaging. This chapter presents a detailed discussion of Deep Learning and Big Data Analytics effects in containment of the disease. In addition, an H2O’s Deep-Learning-inspired model based on Big Data analytics (DLBD-COV) is proposed for early diagnosis of COVID-19 cases using CT or X-ray images. The proposed diagnosis model is build based on the machine learning framework (H2O) for scalable processing. The Generative Adversarial Networks (GAN) and the Convolutional Neural Networks (CNNs) are used and their classification results are compared. The experimental results emphasize the superiority of DLBD-COV when using H(2)O framework for scalable COVID19 classification. The results obtained, using a dataset with thousands of real data and images, show encouraging performance using the automated feature extraction of deep learning techniques used in DLBD-COV.