Covid19 X-rays Image Classification Using Machine Learning and Deep Learning
Nikhil Fande
, Roshan Fande , Rupesh Wadibhasme , Bhavesh Wadibhasme
COVID-19, Coronavirus, Machine Learning, Convolutional Neural Network, Chest X-ray, Support Vector Machine, Logistic Regression
The novel Coronavirus (Covid19) has firstly started in China and widely spread in various countries and approximately 4.1 Million cases have been found worldwide. There are a limited number of COVID-19 testing kits available in hospitals due to gradually increasing in cases on a daily basis. Therefore, in order to increase the testing, it is necessary to implement an auto detection system which will prevent the spread of Covid-19. In this work, we build the binary classifiers based on the machine learning and deep learning models on real image data in predicting positive case probability and provide comparison study of each model. The top features of images have been used for further modeling processes to test stability of binary classifiers by comparing their performance on separate data. We observe that support vector machines (SVM) and Logistic Regression is more stable than convolutional neural networks.
"Covid19 X-rays Image Classification Using Machine Learning and Deep Learning", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.5, Issue 6, page no.651 - 656, June-2020, Available :https://ijsdr.org/papers/IJSDR2006108.pdf
Volume 5
Issue 6,
June-2020
Pages : 651 - 656
Paper Reg. ID: IJSDR_191945
Published Paper Id: IJSDR2006108
Downloads: 000347502
Research Area: Engineering
Country: Gondia, Maharashtra, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
