Research Article
A SVM Based Model for COVID Detection Using CXR Image
@INPROCEEDINGS{10.1007/978-3-030-93709-6_24, author={Sudhir Kumar Mohapatra and Beakal Gizachew Assefa and Getamesay Belayneh}, title={A SVM Based Model for COVID Detection Using CXR Image}, proceedings={Advances of Science and Technology. 9th EAI International Conference, ICAST 2021, Hybrid Event, Bahir Dar, Ethiopia, August 27--29, 2021, Proceedings, Part I}, proceedings_a={ICAST}, year={2022}, month={1}, keywords={CXR Image procession Segmentation COVID Support vector machine}, doi={10.1007/978-3-030-93709-6_24} }- Sudhir Kumar Mohapatra
Beakal Gizachew Assefa
Getamesay Belayneh
Year: 2022
A SVM Based Model for COVID Detection Using CXR Image
ICAST
Springer
DOI: 10.1007/978-3-030-93709-6_24
Abstract
Covid-19 is among the few global pandemic that has caused a massive adverse economic, social, and psychological effect. Nearly hundred million people are affected and out them a minimum of 2 million people lost their lives. The 2nd and 3rd wave of the spread of the virus has been recorded in the western world. Despite the countless efforts and very few successes in preparation of vaccine, the number of people who have access is very much limited even in the developed countries. The RT-PCR and antigen test are impractical in developing and underdeveloped countries because of high cost and less accuracy, respectively. Chest XRay (CXR) has been used for detection of Covid-10, however, it needs a domain expert. In this paper, we propose an Artificial Intelligent assisted automatic radiology system based on CXR images using Support Vector Machines (SVM). Experimental results conducted on real world CXR image data set shows that, our proposed system have achieved an accuracy and sensitivity of 99.4% and 86% respectively..
