Diagnosis of pneumonia in the lungs in the conditions of the COVID-19 pandemic using ensemble learning methods
by Fargana J. Abdullayeva; Suleyman Suleymanzade
International Journal of Reasoning-based Intelligent Systems (IJRIS), Vol. 14, No. 2/3, 2022

Abstract: Chest X-ray (CXR) images play a significant role in the diagnosis of COVID-19 disease in pandemic conditions. However, one of the main problems in determining whether COVID-19 is negative or positive in medical imaging is that the classification models are prone to high false detection rates. The article proposes a system that can accurately assign chest X-ray images of COVID-19 to the appropriate COVID-19 and normal classes. The proposed system consists of two parts: 1) module for feature extraction from images; 2) ensemble learning module that performs the classification of images. Comparative analysis of the proposed approach with the existing methods is provided in numerous experiments, and the advantages of the proposed classification model and the feature extraction method from the previous methods are shown. A model as a result of the experiments, distinguished COVID-19 class images from normal images accurately. As ensemble learning strategies the bagging, pasting and AdaBoost techniques are used.

Online publication date: Fri, 09-Sep-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Reasoning-based Intelligent Systems (IJRIS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com