ABSTRACT
Mask mandate has been applied in many countries in the last two years as a simple but effective way to limit the Covid-19 transmission. Besides the guidance from authorities regarding mask use in public, numerous vision-based approaches have been developed to aid with the monitoring of face mask wearing. Despite promising results have been obtained, several challenges in vision-based masked face detection still remain, primarily due to the insufficient of a quality dataset covering adequate variations in lighting conditions, object scales, mask types, or occlusion levels. In this paper, we investigate the effectiveness of a lightweight masked face detection system under different lighting conditions and the possibility of enhancing its performance with the employment of an image enhancement algorithm and an illumination awareness classifier. A dataset of human subjects with and without face masks in different lighting conditions is first introduced. An illumination awareness classifier is then trained on the collected dataset, the labeling of which is processed automatically based on the difference in detection accuracy when an image enhancement algorithm is taken into account. Experimental results have shown that the combination of the masked face detection system with the illumination awareness and an image enhancement algorithm can boost the system performance to up to 8.6%, 7.4%, and 8.5% in terms of Accuracy, F1-score, and AP-M, respectively. © 2022 IEEE.
ABSTRACT
Background: Soluble Angiotensin Converting Enzyme 2 (ACE2) constitutes an attractive therapeutic candidate with natural resistance to viral escape. To date, ACE2-Fcs, dimeric forms of soluble ACE2, were mostly tested as robust SARS-CoV-2 neutralizers but their potential as antiviral agents capable of Fc-effector functions is largely unknown and has not been tested for effectiveness in vivo, in any model of SARS-CoV2 infection. Methods: We used structure-guided design to select ACE2 mutations that improve SARS-CoV-2 spike (S) affinity and remove angiotensin enzymatic activity. ACE2-Fc variants were engineered into a human IgG1 or IgG3 backbone and produced in mammalian HEK293 cells. S binding was tested by ELISA and surface plasmon resonance (SPR). Mutational effects were validated by X-Ray crystallography. Neutralization activities were measured against SARS-CoV-2 variants of concern (VOCs) using an in vitro pseudovirus (PsV) assay and dynamic bioluminescence imaging (BLI). Antibody-dependent cellular cytotoxicity (ADCC) and antibody-dependent cellular phagocytosis (ADCP) were also quantified using established methods (1, 2). A K18-hACE2 transgenic mouse model challenged by lethal SARS-CoV-2 nLuc infection (3) was used for in vivo evaluation of prophylactic and therapeutic administration of engineered ACE2-Fcs, as monitored by dynamic BLI. Results: Our lead variant, ACE2740 LFMYQY2HA-Fc GASDALIE, increased RBD binding by ∼7-13 fold as compared to wild type, cross-neutralized SARS-CoV-2 VOCs with an IC50 range of 0.23-2.06 nM and mediated robust ADCC and ADCP in vitro. When tested in humanized K18-hACE2 mice, in either a prophylatic or a multi-dosage therapeutic setting, our lead ACE2-Fc variant provided protection from lethal SARS-CoV-2 infection. Our studies in K18-hACE2 mouse model revealed that efficient in vivo efficacy of ACE2-Fcs under prophylaxis or therapeutic settings required Fc-effector functions in addition to neutralization. Conclusion: Our data confirm the utility of engineered ACE2-Fcs as valuable SARS-CoV-2 antivirals and demonstrate that the efficient ACE2-Fc therapeutic activity required both neutralization and Fc-effector functions.
ABSTRACT
Recently, the Covid-19 pandemic has become very complicated and seriously affecting the economy as well as society in every countries in the world. In this chapter, we explore the solution of Computer Vision for handling the Covid-19 pandemic situation. The given scenarios based on deep learning techniques are used to monitor the traffic of people and vehicles through the checkpoints to control the in-out movement in significant areas. In addition, we also need to pay attention to complying with the regulations on wearing masks and ensuring a safe social distance in public places. From there, the proposed system will effectively support organizations to deal with the Covid-19 pandemic. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Environmental protection and high economic growth are the global requirement and have attracted the special attention of researchers and policymakers. Thus, the current study is also going to examine the impact of green finance that includes green investment and green loan on the economic growth of Vietnam. The data have been obtained from the central bank of Vietnam and World Bank Indicators (WDI) from 1986 to 2019. This study also executed the Autoregressive Distributed Lag (ARDL) approach to examine the links among the variables. The results exposed that green finance along with all control variables have a positive association with economic growth. These outcomes have guided regulators to increase their focus on green finance that could increase the economic growth in the country.