Training CNN To Categorize Pulmonary Radiological Imaging

( An International Open Access , Peer-reviewed, Refereed Journal )

IJIRTEXPLORE- Search Thousands of research papers

ISSN: 2349-6002 ESTD Year: 2014

UGC approved journal no 47859

Training CNN To Categorize Pulmonary Radiological Imaging
Author(s):
Asawari Pensalwar, Mallisha Patkar, Rachana Dhannawat
Keywords:
CNN, Chest x-ray,covid-19 Detection
Abstract
Covid-19 is a severe acute respiratory syndrome that can be spread by close contact with an infected person. In this paper, we have proposed two convolutional neural network architectures to classify the image and see if the patient has COVID-19 or not. The first proposed architecture is using dropout layer and the other is without the dropout layer. The models are tested for two datasets: the original dataset and the dataset with augmentation. After testing, we got the highest accuracy of 98% with model 4 i.e. without dropout layer and with no data augmentation. We combined this model with webpage which can be used by normal people to know whether they are suffering from COVID-19 or not with probability of its occurrence.
Article Details
Unique Paper ID: 151650 Publication Volume & Issue: Volume 8, Issue 1 Page(s): 455 - 461
Article Preview & Download

Share This Article

International conference on Management, Science, Technology, Engineering, Pharmact and Humanities.

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org