Why Are Generative Adversarial Networks Vital for Deep Neural Networks? A Case Study on COVID-19 Chest X-Ray Images

Shams, M. Y.; Elzeki, O. M.; Abd Elfattah, Mohamed; Medhat, T.; Hassanien, Aboul Ella

The need to generate large scale datasets from a limited number of determined data is highly required. Deep neural networks (DNN) is one of the most important and effective tools in machine learning (ML) that required large scale datasets. Recently, generative adversarial networks (GAN) is considered as the most potent and effective method for data augmentation. In this chapter, we investigated the importance of using GAN as a preprocessing stage to applied DNN for image data augmentation. Moreover, we present a case study of using GAN networks for a limited COVID-19 X-Ray Chest images. The results indicate that the proposed system based on using GAN-DNN is powerful with minimum loss function for detecting COVID-19 X-Ray Chest images. Stochastic gradient descent (SGD) and Improved Adam (IAdam) optimizers are used during the training process of the COVID-19 X-Ray images, and the evaluation results depend on loss function are determined to ensure the reliability of the proposed GAN architecture.