A systematic mapping review of COVID-19 data feature for infection detection

Siddiqa Javaid; Tayyaba Rasool; Umara Noor; Zakia Jalil; Zahid Rashid

doi:10.22581/muet1982.2536

Siddiqa Javaid Department of Software Engineering, International Islamic University Islamabad, Pakistan
Tayyaba Rasool Department of Software Engineering, International Islamic University Islamabad, Pakistan
Umara Noor Department of Software Engineering, International Islamic University Islamabad, Pakistan http://orcid.org/0000-0001-8135-8140
Zakia Jalil Department of Software Engineering, International Islamic University Islamabad, Pakistan
Zahid Rashid College of Engineering, Seoul National University, 1 Gwanak-Ro, Gwanak-Gu, 08826, Seoul, South Korea http://orcid.org/0000-0003-4786-049X

DOI: https://doi.org/10.22581/muet1982.2536

Abstract

The coronavirus disease (COVID-19) has become widespread. It has caused outbreaks in more than 213 nations leading to many fatalities. It is still going around in all its forms. The diagnosis, prognosis, and treatment of disease include a variety of novel approaches, including machine learning, artificial intelligence, and the Internet of Things (IoT). Numerous studies on the detection of COVID-19 using various techniques have been conducted. Numerous strategies are used and suggested in the literature. This study aims to pinpoint the data features of COVID-19 that have been employed for disease detection by IoT devices using machine learning techniques. This research project offers a comprehensive mapping and evaluation of current studies on COVID-19. The focus is on IoT gadgets employing machine learning for detection. The study is conducted using a systematic mapping review. For the mapping study review, five electronic databases were searched. Studies published until April 2022 were considered. There are 50 studies selected that address COVID-19, IoT devices, and machine-learning approaches. This research concludes the investigation of data features that are usually used for effective, and efficient detection. This research will be useful for a future COVID-19 variant pandemic, as it provides a comprehensive review of the best data features for disease detection. Also, the data features identified in this research can aid in the early and precise exposure of COVID-19 in existing circumstances.