AUTHOR=Khan Habib Ullah , Khan Sulaiman , Nazir Shah 

TITLE=A Novel Deep Learning and Ensemble Learning Mechanism for Delta-Type COVID-19 Detection

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.875971

DOI=10.3389/fpubh.2022.875971

ISSN=2296-2565

ABSTRACT=– Recently, the novel corona virus disease (Covid-19) has posed many challenges to the research community by presenting grievous acute respiratory syndrome coronavirus-2 (SARS-COV-2), results with a huge number of mortalities and high morbidities worldwide. Furthermore, the symptoms based variations in virus type add new challenges for the research and practitioners to combat. Covid infected patients comprises trenchant radiographic visual features including dry cough, fever, dyspnea, fatigue, etc. Chest x-ray is considered as a simple and non-invasive clinical adjutant that perform a key role for the identification of these ocular responses related with Convid-19 infection. Nevertheless, the defined availability of proficient radiologists to understand the x-ray images and elusive aspect of disease radiographic replies remnant the biggest bottlenecks in manual diagnosis. To address these issues, the proposed research work presents a hybrid deep learning model for the accurate diagnosing of Delta Type Covid-19 infection using x-ray images. This hybrid model comprises visual geometry group (VGG16) and support vector machine (SVM), where the VGG16 is accustomed for the identification process while the SVM is used for the severity-based analysis of the infected people. An overall accuracy rate of 97.37% is recorded for the assumed model. Other performance metrics such as area under curve (AUC), precision, F-score, miss-classification rate, and confusion matrix are used for the validation and analysis purposes. Finally, the applicability of the presumed model is assimilated with other avant techniques. The high identification rates shines the applicability of the formulated hybrid model in the targeted research domain.