A Novel Machine Learning Framework for Tracing Covid Contact Details by Using Time Series Locational data & Prediction Techniques

Abstract

It is difficult to prevent the spread of new infections in densely populated areas because they spread at a faster rate. One of the most commonly used techniques for this type of scenario is contact tracing, which involves locating the infected character and his close contacts after he has been infected. This is one of the most recent and effective methods that the health authorities have supported. We can see Machine Learning strategies that require some region information to efficiently implement contact tracing. Contact tracing is used by local governments and health authorities to halt the spread of rapidly spreading diseases. It is one of the locally focused methods that work well when the number of cases is small. As a result, we can say that it can be or is primarily used in rapidly transmitted diseases and newly emerging infections. Using cluster-based region identifications, the utility of touch tracing is investigated using nearest neighbour approaches and absolute deterministic simulations (MLDBSCAN). Emerging or re-emerging infectious diseases like SARS, Ebola, Lassa fever, tuberculosis, and, most recently, COVID-19 require extremely effective prevention methods and strategies.