Sharif Digital Repository

Humanity's challenges are becoming increasingly difficult, and as these challenges become more advanced, the need for effective and intelligent action becomes more apparent. Meanwhile, the novel coronavirus disease (COVID-19) pandemic, which has plagued the world, could be considered as an opportunity to take a step toward the need for atomic engineering, compared to molecular engineering, as well as to accelerate this type of research. This approach, which can be expressed in terms of picotechnology, makes it possible to identify living cell types or in general, chemical and biological surfaces using their atomic arrays, and applied for early diagnosis even treatment of the disease. © 2020... 

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) caused the COVID-19 pandemic that has been spreading around the world since December 2019. More than 10 million affected cases and more than half a million deaths have been reported so far, while no vaccine is yet available as a treatment. Considering the global healthcare urgency, several techniques, including whole genome sequencing and computed tomography imaging have been employed for diagnosing infected people. Considerable efforts are also directed at detecting and preventing different modes of community transmission. Among them is the rapid detection of virus presence on different surfaces with which people may come in... 

In this paper, we have trained several deep convolutional networks with introduced training techniques for classifying X-ray images into three classes: normal, pneumonia, and COVID-19, based on two open-source datasets. Our data contains 180 X-ray images that belong to persons infected with COVID-19, and we attempted to apply methods to achieve the best possible results. In this research, we introduce some training techniques that help the network learn better when we have an unbalanced dataset (fewer cases of COVID-19 along with more cases from other classes). We also propose a neural network that is a concatenation of the Xception and ResNet50V2 networks. This network achieved the best...