COUNTERSAVIOR: AIoMT and IIoT-Enabled Adaptive Virus Outbreak Discovery Framework for Healthcare Informatics

• Published in: IEEE internet of things journal Vol. 10; no. 5; pp. 4202 - 4212
• Main Authors: Pandya, Sharnil, Ghayvat, Hemant, Reddy, Praveen Kumar, Gadekallu, Thippa Reddy, Khan, Muhammad Ahmed, Kumar, Neeraj
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.03.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial intelligence; Artificial Intelligence of Medical Things (AIoMT); Big Data; Computer and Information Sciences Computer Science; Coronaviruses; COVID-19; Data- och informationsvetenskap; Deep learning; Disease transmission; Diseases; edgeline computing; Edgelines; Forecasting; Global Positioning System; global positioning system (GPS) big data; Global positioning systems; GPS; Health Informatics; Hälsoinformatik; Machine learning; Outbreaks; Pandemics; Real-time systems; Safety; Servers; Spatial data; Spatiotemporal data; Viral diseases; Viruses
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2022.3216108

In the current pandemic, global issues have caused health issues as well as economic downturns. At the beginning of every novel virus outbreak, lockdown is the best possible weapon to reduce the virus spread and save human life as the medical diagnosis followed by treatment and clinical approval takes significant time. The proposed COUNTERSAVIOR system aims at an Artificial Intelligence of Medical Things (AIoMT), and an edge line computing enabled and Big data analytics supported tracing and tracking approach that consumes global positioning system (GPS) spatiotemporal data. COUNTERSAVIOR will be a better scientific tool to handle any virus outbreak. The proposed research discovers the prospect of applying an individual's mobility to label mobility streams and forecast a virus such as COVID-19 pandemic transmission. The proposed system is the extension of the previously proposed COUNTERACT system. The proposed system can also identify the alternative saviour path concerning the confirmed subject's cross-path using GPS data to avoid the possibility of infections. In the undertaken study, dynamic meta direct and indirect transmission, meta behavior, and meta transmission saviour models are presented. In conducted experiments, the machine learning and deep learning methodologies have been used with the recorded historical location data for forecasting the behavior patterns of confirmed and suspected individuals and a robust comparative analysis is also presented. The proposed system produces a report specifying people that have been exposed to the virus and notifying users about available pandemic saviour paths. In the end, we have represented 3-D tracker movements of individuals, 3-D contact analysis of COVID-19 and suspected individuals for 24 h, forecasting and risk classification of COVID-19, suspected and safe individuals.