ABSTRACT
The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the reso-lution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at x3 SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.
ABSTRACT
Since the outbreak of the COVID-19, comprehensive and thorough environmental disinfection is a very important issue. In order to reduce personnel contact and reduce the risk of cross-infection, this paper designs an indoor disinfecting intelligent robot that can realize large-scale combined disinfection of disinfectant and ultraviolet. The whole system comprises of five main parts: control center, running control module, disinfection module, information processing module, and power module. The control center mainly adopts ESP32micro-controller to achieve the connection and control of all parts of the system. The running control module mainly controls the forward, backward, and rotation of the device and ensures that the system follows the expected path during the disinfection. The disinfection module uses liquid disinfectant and ultraviolet irradiation to inhibit the bacteria and kill COVID-19. Information processing module is responsible for the information interaction between the system and the data center. The proposed system transmits data through Wi-Fi and MQTT protocol, and realizes basic functions such as positioning, path planning, and disinfection. The proposed system can effectively solve the problem of personal contact and infection in the process of manual disinfection and have nice application value. © 2022 IEEE.
ABSTRACT
Corona Virus Disease 2019 (COVID-19) has seriously threatened human life and health in just a few months. The global economy, education, transportation and other aspects have been affected. In order to solve the problems caused by COVID-19 as soon as possible, it is important to quickly and accurately confirm whether people are infected. In this paper, we take MultiResUNet as the basic model, introduce a new "Residual block" structure in the encoder part, add Regularization and Dropout to prevent training overfilling, and change the partial activation function. Propose a model suitable for COVID-19 CT image sets, which can automatically segment four parts of COVID-19 CT images (left&right lung, disease and background) by deep learning. The segmentation results are evaluated and the expected results are achieved. It is helpful for medical workers to recognize the infection area quickly.
ABSTRACT
Serious traffic-related pollution and high population density during the spring festival (Chinese new year) travel rush (SFTR) increases the travelers' exposure risk to pollutants and biohazards. This study investigates personal exposure to particulate matter (PM) mass concentration when commuting in five transportation modes during and after the 2020 SFTR: China railway highspeed train (CRH train), subway, bus, car, and walking. The routes are selected between Nanjing and Xuzhou, two major transportation hubs in the Yangtze Delta. The results indicate that personal exposure levels to PM on the CRH train are the lowest and relatively stable, and so it is recommended to take the CRH train back home during the SFTR to reduce the personal PM exposure. The exposure level to PM2.5 during SFTR is twice as high as the average level of Asia, and it is higher than the WHO air quality guideline (AQG).
ABSTRACT
Coronavirus ( CoV) is a class of enveloped, positive-sense single-stranded RNA viruses which can infect humans and animals. At the end of 2019, a novel beta-coronavirus SARS-CoV-2 ( Severe acute respiratory syndrome-coronavirus-2) has started to spread from person to person, and the virus-related disease "COVID-19" ( Coronavirus disease 2019) poses a serious threat to global public health in different countries. Glycosylation is a post-translational modification that exists on proteins, which can affect the protein folding, stability, and the binding between virus and host receptors. Spike ( S) protein determines the tropism of the virus to the host. A plenty of studies have shown that the spike( S) protein in the SARS-CoV-2 envelope and the main receptor on the host cell, Angiotensin converting enzyme 2 ( ACE2), are highly glycosylated proteins. To explore the role of glycosylation in virus infection and host immune response, this review summarizes the infection mechanism of SARS-CoV-2, the glycosylation modifications of recombinant S protein and host receptor protein ACE2, and the effects of glycosylation on the interaction between virus and host cells. Finally, based on the mechanism of glycosylation, we propose novel potential strategies for COVID-19 diagnosis and anti-virus drug development, which provides new directions for the diagnosis and treatment of COVID-19.