ABSTRACT
The outbreak of coronavirus disease 2019 (COVID-19) occurred at the end of 2019, and it has continued to be a source of misery for millions of people and companies well into 2020. There is a surge of concern among all persons, especially those who wish to resume in-person activities, as the globe recovers from the epidemic and intends to return to a level of normalcy. Wearing a face mask greatly decreases the likelihood of viral transmission and gives a sense of security, according to studies. However, manually tracking the execution of this regulation is not possible. The key to this is technology. We present a deep learning-based system that can detect instances of improper use of face masks. A dual-stage convolutional neural network architecture is used in our system to recognize masked and unmasked faces. This will aid in the tracking of safety breaches, the promotion of face mask use, and the maintenance of a safe working environment. In this paper, we propose a variant of a multi-face detection model which has the potential to target and identify a group of people whether they are wearing masks or not.
ABSTRACT
The COVID-19 epidemic has exerted significant impacts on human health, social and economic activities, air quality and atmospheric chemistry, and potentially on climate change. In this study, an online coupled regional climate-chemistry-aerosol model (RIEMS-Chem) was applied to explore the direct, indirect, and feedback effects of anthropogenic aerosols on radiation, boundary layer meteorology, and fine particulate matter during the COVID-19 lockdown period from 23 January to 8 April 2020 over China. Model performance was validated against a variety of observations for meteorological variables, PM2.5 and its chemical components, aerosol optical properties, as well as shortwave radiation flux, which demonstrated that RIEMS-Chem was able to reproduce the spatial distribution and temporal variation of the above variables reasonably well. During the study period, direct radiative effect (DRE) of anthropogenic aerosols was stronger than indirect radiative effect (IRE) in most regions north of the Yangtze River, whereas IRE dominated over DRE in the Yangtze River regions and South China. In North China, DRE induced larger changes in meteorology and PM2.5 than those induced by IRE, whereas in South China, the changes by IRE were remarkably larger than those by DRE. Emission reduction alone during the COVID-19 lockdown reduced PM2.5 concentration by approximately 32 % on average over East China. As a result, DRE at the surface was weakened by 15 %, whereas IRE changed little over East China, leading to a decrease in total radiative effect (TRE) by approximately 7 % in terms of domain average. The DRE-induced changes in meteorology and PM2.5 were weakened due to emission reduction, whereas the IRE-induced changes were almost the same between the cases with and without emission reductions. By aerosol radiative and feedback effects, the COVID-19 emission reductions resulted in 0.06 °C and 0.04 °C surface warming, 1.6 and 4.0 µg m-3 PM2.5 decrease, 0.4 and 1.3 mm precipitation increase during the lockdown period in 2020 in terms of domain average over North China and South China, respectively, whereas the lockdown caused negligible changes on average over East Asia.