Abstract

More than a year since the novel coronavirus was first discovered, its presence is
still prevalent throughout the world. In such grave situations if technology can help
humans combat the spread, then why not explore it. Therefore, keeping this in mind,
several researchers have already started investigating artificial intelligence algorithms to
find solutions to predict coronavirus using X-ray images of chest. But due to lack of
dataset during the initial days of their research, many came up with framework using pre
trained image classification models such as VGG-16, Inceptionv3, ResNet-50 and others.
In this paper, the performance of two machine learning algorithms which are support
vector machine and decision tree has been evaluated. Further developed deep learning
model applying convolutional neural network to classify the chest x-ray images as covid-19
or normal. The final CNN model was also integrated with a user interface and hosted on
web server for easy access which allows anyone to upload the chest x-ray image from his
computer or mobile and check the result.