To search, Click below search items.


All Published Papers Search Service


Benchmarking Multiple Deep Learning Models for Enhanced COVID-19 Detection


Sadeem Alharthi, Shahad Alqurashi, Manal Alamir, Manal AlGhamdi, Tahani Alsubait


Vol. 20  No. 8  pp. 112-118


======= DOI: 10.22937/IJCSNS.2020.20.08.11 ======= Due to the recent emergence of COVID-19, chaos and economic destruction have spread all around the world. As this is considered a novel virus, lack of resources and limitations of planning to cope with this pandemic have greatly impacted many lives and many people have lost their loved ones due to this situation. Thus, there is a need for some innovation of science and AI to handle this task on hand. It has become very necessary to investigate the use of the latest deep learning modeling techniques to discover efficient ways of detection of this novel virus. In this paper, we used publicly available datasets to apply some deep learning modeling techniques including VGG19, Xception, Resnet50 and GoogleNet in a transfer learning manner. Using such models eases the process of detection of the disease from chest X-rays to classify the patients based on their status: either COVID-19 or pneumonia chest/normal patients. The achieved preliminary results are promising. In particular, the Xception model achieves the highest performance with 99%, whereas the accuracy of the VGG19, ResNet50 and the InceptionV3 are 98%, 98%, and 90% respectively.


COVID-19, Corona Virus, Chest X-Ray, Convolutional Neural Network, Deep Neural Network