A Novel COVID-19 Diagnostic System Using Biosensor Incorporated Artificial Intelligence Technique
Md. Mottahir Alam,
Md. Moddassir Alam,
Hidayath Mirza,
Nishat Sultana,
Nazia Sultana,
Amjad Ali Pasha,
Asif Irshad Khan,
Aasim Zafar,
Mohammad Tauheed Ahmad
Affiliations
Md. Mottahir Alam
Department of Electrical and Computer Engineering, Faculty of Engineering, King Abdulaziz, Jeddah 21589, Saudi Arabia
Md. Moddassir Alam
Department of Health Information Management and Technology, College of Applied Medical Sciences, University of Hafr Al-Batin, Hafr Al-Batin 39524, Saudi Arabia
Hidayath Mirza
Department of Electrical Engineering, College of Engineering, Jazan University, P.O. Box 706, Jazan 45142, Saudi Arabia
Nishat Sultana
Department of Business Administration, Applied College, Jazan University, P.O. Box 706, Jazan 45142, Saudi Arabia
Nazia Sultana
Government Medical College Siddipet, Ensanpalli, Siddipet District, Telangana 502114, India
Amjad Ali Pasha
Aerospace Engineering Department, King Abdulaziz University, Jeddah 21589, Saudi Arabia
Asif Irshad Khan
Computer Science Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia
Aasim Zafar
Department of Computer Science, Aligarh Muslim University, Aligarh 202002, India
Mohammad Tauheed Ahmad
College of Medicine, King Khalid University, Abha 62217, Saudi Arabia
COVID-19, continually developing and raising increasingly significant issues, has impacted human health and caused countless deaths. It is an infectious disease with a high incidence and mortality rate. The spread of the disease is also a significant threat to human health, especially in the developing world. This study suggests a method called shuffle shepherd optimization-based generalized deep convolutional fuzzy network (SSO-GDCFN) to diagnose the COVID-19 disease state, types, and recovered categories. The results show that the accuracy of the proposed method is as high as 99.99%; similarly, precision is 99.98%; sensitivity/recall is 100%; specificity is 95%; kappa is 0.965%; AUC is 0.88%; and MSE is less than 0.07% as well as 25 s. Moreover, the performance of the suggested method has been confirmed by comparison of the simulation results from the proposed approach with those from several traditional techniques. The experimental findings demonstrate strong performance and high accuracy for categorizing COVID-19 stages with minimal reclassifications over the conventional methods.
