Open AccessFinding an optimal distance of social distancing for COVID 19
Author(s) -
J. Samuel Manoharan
Publication year - 2021
Publication title -
journal of ismac the journal of iot in social, mobile, analytics, and cloud
Language(s) - English
Resource type - Journals
ISSN - 2582-1369
DOI - 10.36548/jismac.2021.3.003
Subject(s) - social distance , covid-19 , transmission (telecommunications) , computer science , pandemic , identification (biology) , distancing , artificial intelligence , computer security , machine learning , risk analysis (engineering) , data science , business , medicine , disease , telecommunications , botany , pathology , infectious disease (medical specialty) , biology
Social distancing is a non-pharmaceutical infection prevention and control approach that is now being utilized in the COVID-19 scenario to avoid or restrict the transmission of illness in a community. As a consequence, the disease transmission, as well as the morbidity and mortality associated with it are reduced. The deadly coronavirus will circulate if the distance between the two persons in each site is used. However, coronavirus exposure must be avoided at all costs. The distance varies due to different nations' political rules and the conditions of their medical embassy. The WHO established a social distance of 1 to 2 metres as the standard. This research work has developed a computational method for estimating the impact of coronavirus based on various social distancing metrics. Generally, in COVID – 19 situations, social distance ranging from long to extremely long can be a good strategy. The adoption of extremely small social distance is a harmful approach to the pandemic. This calculation can be done by using deep learning based on crowd image identification. The proposed work has been utilized to find the optimal social distancing for COVID – 19 and it is identified as 1.89 meter. The purpose of the proposed experiment is to compare the different types of deep learning based image recognition algorithms in a crowded environment. The performance can be measured with various metrics such as accuracy, precision, recall, and true detection rate.