ABSTRACT
With the COVID-19 outbreak in 2019, the world is facing a major crisis and people's health is at serious risk. Accurate segmentation of lesions in CT images can help doctors understand disease infections, prescribe the right medicine and control patients' conditions. Fast and accurate diagnosis not only can make the limited medical resources get reasonable allocation, but also can control the spread of disease, and computer-aided diagnosis can achieve this purpose, so this paper proposes a deep learning segmentation network LLDSNet based on a small amount of data, which is divided into two modules: contextual feature-aware module (CFAM) and shape edge detection module (SEDM). Due to the different morphology of lesions in different CT, lesions with dispersion, small lesion area and background area imbalance, lesion area and normal area boundary blurred, etc. The problem of lesion segmentation in COVID-19 poses a major challenge. The CFAM can effectively extract the overall and local features, and the SEDM can accurately find the edges of the lesion area to segment the lesions in this area. The hybrid loss function is used to avoid the class imbalance problem and improve the overall network performance. It is demonstrated that LLDSNet dice achieves 0.696 for a small number of data sets, and the best performance compared to five currently popular segmentation networks. © 2023 SPIE.
ABSTRACT
A new pattern of oil trade has emerged under the influence of geopolitics and the COVID-19 pandemic. To explore China's oil security in these changed times, this study takes the new pattern of global oil trade as the background and adopts the oil trade models of Russia, India, Saudi Arabia, and China itself. Since Saudi Arabia's oil trade with China and India has been safe and stable for long, this study uses evolutionary game theory to make a quantitative analysis of the energy competition between China and India and the energy cooperation between China and Russia. The research results reveal the following: 1) The continued increase in India's Russian oil imports will pose a threat to China's oil security. When India's oil imports from Russia reach 16.5%, it will change the oil trade structure of the four countries and become a crucial threat to China and 2) Russia's willingness to export has a direct impact on the results. As Russia's willingness to export declines, it will affect the results and pose a threat to China's oil security. This study is of great significance as it provides meaningful insights to ensure China's oil security in the post pandemic era with key changes in the world's oil trade pattern. © 2023 Science Press. All rights reserved.
ABSTRACT
Global pandemic due to the spread of COVID-19 has post challenges in a new dimension on facial recognition, where people start to wear masks. Under such condition, the authors consider utilizing machine learning in image inpainting to tackle the problem, by complete the possible face that is originally covered in mask. In particular, autoencoder has great potential on retaining important, general features of the image as well as the generative power of the generative adversarial network (GAN). The authors implement a combination of the two models, context encoders and explain how it combines the power of the two models and train the model with 50,000 images of influencers faces and yields a solid result that still contains space for improvements. Furthermore, the authors discuss some shortcomings with the model, their possible improvements, as well as some area of study for future investigation for applicative perspective, as well as directions to further enhance and refine the model. © 2023 SPIE.
ABSTRACT
We live in a world of borders, which influence our perception and movement. Traditional mapping techniques show limitations as borders have become shifting and complex, and borders' multi-scale and multi-spatial properties have been strengthened significantly. To fill the knowledge gap, we explored the multi-spatiality of borders and provided approaches for border symbol design and visualization by taking the coronavirus-hit border city, Ruili, China, as an example. This work could shed light on multi-spatial geographic visualization and policy-making.
ABSTRACT
Many countries have implemented school closures due to the outbreak of the COVID-19 pandemic, which has inevitably affected children's physical and mental health. It is vital for parents to pay special attention to their children's health status during school closures. However, it is difficult for parents to recognize the changes in their children's health, especially without visible symptoms, such as psychosocial functioning in mental health. Moreover, healthcare resources and understanding of the health and societal impact of COVID-19 are quite limited during the pandemic. Against this background, we collected real-world datasets from 1,172 children in Hong Kong during four time periods under different pandemic and school closure conditions from September 2019 to January 2022. Based on these data, we first perform exploratory data analysis to explore the impact of school closures on six health indicators, including physical activity intensity, physical functioning, self-rated health, psychosocial functioning, resilience, and connectedness. We further study the correlation between children's contextual characteristics (i.e., demographics, socioeconomic status, electronic device usage patterns, financial satisfaction, academic performance, sleep pattern, exercise habits, and dietary patterns) and the six health indicators. Subsequently, a health inference system is designed and developed to infer children's health status based on their contextual features to derive the risk factors of the six health indicators. The evaluation and case studies on real-world datasets show that this health inference system can help parents and authorities better understand key factors correlated with children's health status during school closures. © 2023 ACM.
ABSTRACT
Objective This study aimed to examine the epidemic characteristics of the COVID-19 imported cases entering mainland China from March 4, 2020 to October 31, 2021, so as to provide the reference for the prevention and control of imported epidemic at present. Methods Data were collected from the Daily Summary on the COVID-19 epidemic issued by the national/provincial health commission official website from March 4, 2020 to October 31, 2021, including " number of imported cases and existing imported cases and source country/territory and destination province for imported cases. Joinpoint regression was used to examine the time trends in the number of imported cases over time. Results From March 4, 2020 to November 3, 2021, the number of monthly newly imported cases and existing confirmed cases changed as a " W” shape. The imported cases came from 152 counties and territories in total, mainly from Myanmar, United States, Philippines and Russia (accounting for 27.6% of all imported cases). The number of imported cases mainly entered Shanghai, Guangdong, Yunnan, Sichuan, and Fujian, explaining 70.59% of total imported cases. Conclusions The great fluctuating change of imported cases in the mainland of China may be related to the change of global COVID-19 epidemic and domestic prevention and control policies. Considering the imbalanced distribution of source country/territory and destination province of imported cases, the government should take targeted measures in important source countries/terriories and destination provinces. Each province and municipality should modify its policy for preventing the imported epidemic dynamically according to the latest characteristic of source country/territory and virus mutation. © 2023, Publication Centre of Anhui Medical University. All rights reserved.
ABSTRACT
Objective This study aimed to examine the epidemic characteristics of the COVID-19 imported cases entering mainland China from March 4, 2020 to October 31, 2021, so as to provide the reference for the prevention and control of imported epidemic at present. Methods Data were collected from the Daily Summary on the COVID-19 epidemic issued by the national/provincial health commission official website from March 4, 2020 to October 31, 2021, including " number of imported cases and existing imported cases and source country/territory and destination province for imported cases. Joinpoint regression was used to examine the time trends in the number of imported cases over time. Results From March 4, 2020 to November 3, 2021, the number of monthly newly imported cases and existing confirmed cases changed as a " W" shape. The imported cases came from 152 counties and territories in total, mainly from Myanmar, United States, Philippines and Russia (accounting for 27.6% of all imported cases). The number of imported cases mainly entered Shanghai, Guangdong, Yunnan, Sichuan, and Fujian, explaining 70.59% of total imported cases. Conclusions The great fluctuating change of imported cases in the mainland of China may be related to the change of global COVID-19 epidemic and domestic prevention and control policies. Considering the imbalanced distribution of source country/territory and destination province of imported cases, the government should take targeted measures in important source countries/terriories and destination provinces. Each province and municipality should modify its policy for preventing the imported epidemic dynamically according to the latest characteristic of source country/territory and virus mutation.Copyright © 2023, Publication Centre of Anhui Medical University. All rights reserved.
ABSTRACT
This study investigates the spillover dynamics among 10 Australian sectoral indices and their connectedness to global factors, including the WTI crude oil price, oil market volatility, Australian exchange rate, U.S. stock market volatility index and Infectious Disease Tracker Index. Using data from May 14, 2007 to March 31, 2022, this study applies the time-varying parameter vector autoregressive model to study their static and dynamic connectedness, wavelet coherence analysis to investigate the time-frequency co-movement of global macroeconomic factors with Australian sector stock indices and wavelet decomposition-based Granger causality. The results show that aggressive stocks (Industrials, Consumer Discretionary and Financials) are net transmitters, while defensive stocks (Health, Information Technology, Communication and Utilities) are net receivers of spillovers. The coronavirus pandemic has increased systemic risk, causing radical changes in net connectedness. Additionally, global macroeconomic factors drive the connectedness of the Australian sectoral indices, with oil and exchange rates moving in phase, and oil volatility, stock volatility and the Infectious Disease Tracker Index moving in antiphase. Global stock and oil market volatility has a significant impact on the Australian sector's returns over short-, medium- and long-term horizons. This study provides valuable insights to investors and policymakers by carefully examining the relationships between global factors and Australian sectoral indices. © 2023 John Wiley & Sons Australia, Ltd.
ABSTRACT
For normalized prevention and control of novel corona virus disease 2019 (COVID-19) pandemic, a robot system is desired to assist in performing large numbers of oropharyngeal (OP) swab sampling. However, reliability and efficiency are still challenges for the practical application of existing robot systems. In this paper, a robot system and related implementation scheme for high efficiency automatic OP swab sampling are developed. A novel robot end-effector with a disposable protective cover is designed, that testee keeps biting on its terminal during sampling. The main steps of the sampling procedure, including sterilizing, recycling, swab mounting and collection, are realized automatically. The effectiveness and efficiency of the proposed robot system are validated through experiment on human subjects. The whole sampling procedure takes about 80 to 90 seconds. © 2022 IEEE.
ABSTRACT
In the aftermath of COVID-19, remote working has become the norm, and graduates now need an even wider range of skills, which traditional classrooms and internships do not always provide. Working in multiple time zones, within global multi-cultural teams, and only ever meeting colleagues through online technology are just some of the challenges, which require a new type of global graduate. Transversal skills including leadership, collaboration, innovation, digital, green, organization and communication skills are critical. The disruption from COVID-19 also presents unprecedented opportunities to develop more inclusive approaches to internships and international experiences, to level the playing field for students with special needs, from underrepresented groups or with caring commitments. In this position paper, we present a new Global Innovation internship model that has the aim of allowing students to complete technology internships and projects by working together virtually on real world challenges, guided by experienced industry and academic mentors. The model is being developed as part of an Erasmus+ funded project, and the partnership includes seven Higher Education Institutions from six different countries around the world. This position paper describes the design and development of a pilot programme of the Global Innovations internship model. Copyright © 2022 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.
ABSTRACT
After Covid-19 swept the globe and bitcoin prices suddenly soared, machine learnings were used to predict the trend of bitcoin prices, but these studies were lack of performance analysis in different time-scale span. In this paper, three neural network models are designed and used to forecast the price of bitcoin after the outbreak of COVID-19. The models A uses the high/low price, open/close price of four-days of bitcoin as input variables and the close price of the fifth day as target variable, the models B uses same variable as the model A and uses optimal weights, and the model C uses same structure as the model B, but adds the trading volume to the input variables. The results show that the model C may lower the difference between actual and calculated outputs, thus boosting the prediction accuracy. Also, it is found that the models that can work well when predicting bitcoin prices in a short time span can be obviously less precise when it comes to predicting bitcoin prices in a longer time span. © 2022 ACM.
ABSTRACT
Given COVID-19's disproportionate adverse impact on hospitality employees, we explore the proposition that COVID-19-related career challenges prompt CALD hospitality workers to rethink the meaning and purpose of work to explore ways to cope and restore occupational well-being, thus triggering occupational change. Thematic analysis of qualitative data from interviews with 25 CALD hotel workers reveal different sub-groups of CALD hotel workers differentially cognitively frame pandemic-induced employment changes to cope and restore occupational well-being: 1. as an opportunity for behavioral (occupational) change by CALD workers in refugee jobs;2. as a temporary phenomenon, with CALD workers who were temporary migrants foreseeing positive career outcomes;and 3. as an opportunity for behavioral (occupational) advancement in hotels by CALD workers who were permanent residents with hospitality qualifications. We contribute to literature at the intersection of coping and occupational well-being research in hospitality, providing a fine-grained understanding of how CALD hotel workers coped and restored occupational well-being, by differentially reconstruing the meaning of work and undertaking occupational change, be it cognitive or behavioral.
ABSTRACT
The present study explored the inflammatory response and clinical efficacy of Tanreqing injection in combination with antiviral therapy in patients with coronavirus disease (COVID-19). The results demonstrated that the levels of C-reactive protein (CRP) and interleukin-6 (IL-6) in the treatment group were significantly lower than those in the control group (p < 0.05). Clinical efficacy assessment revealed a significant improvement in the time necessary for image absorption improvement in the treatment group (p < 0.05), while the time taken for fever and muscle soreness symptoms to resolve significantly reduced (p < 0.05). Furthermore, the time taken to obtain a negative COVID-19 test result was significantly shortened (p < 0.05). Tanreqing injection combined with antiviral treatment improved clinical symptoms of COVID-19 faster than when the anti-viral treatments were used alone and this may be related to the reduction in inflammatory response. Copyright © 2022, Colegio de Farmaceuticos de la Provincia de Buenos Aires. All rights reserved.
ABSTRACT
The growing need for technology that supports remote healthcare is being acutely highlighted by an aging population and the COVID-19 pandemic. In health-related machine learning applications the ability to learn predictive models without data leaving a private device is attractive, especially when these data might contain features (e.g., photographs or videos of the body) that make identifying a subject trivial and/or the training data volume is large (e.g., uncompressed video). Camera-based remote physiological sensing facilitates scalable and low-cost measurement, but is a prime example of a task that involves analysing high bit-rate videos containing identifiable images and sensitive health information. Federated learning enables privacy-preserving decentralized training which has several properties beneficial for camera-based sensing. We develop the first mobile federated learning camera-based sensing system and show that it can perform competitively with traditional state-of-the-art supervised approaches. However, in the presence of corrupted data (e.g., video or label noise) from a few devices the performance of weight averaging quickly degrades. To address this, we leverage knowledge about the expected noise profile within the video to intelligently adjust how the model weights are averaged on the server. Our results show that this significantly improves upon the robustness of models even when the signal-to-noise ratio is low. © 2022 IEEE.
ABSTRACT
With the development of Deep Learning, image recognition technology has been applied in many aspects. And convolutional neural networks have played a key role in realizing image recognition under the increasing computing power and massive data. However, if developers want to implement the training of convolutional neural networks and achieve the subsequent applications in scenarios such as personal computers, IoT devices, and embedded platforms with low Graphics Processing Units(GPUs) memory, a large number of parameters during training of convolutional neural networks is a great challenge. Therefore, this paper uses depthwise separable convolution to optimize the classic convolutional neural network model VGG-16 to solve this problem. And the VGG-16-JS model is proposed using the Inception structure dimensionality reduction and depthwise separable convolution on the VGG-16 convolutional neural network model. Finally, this paper compares the classification success rates of VGG-16 and VGG-16-JS for the application scenario of the COVID-19 mask-wearing. A series of reliable experimental data show that the improved VGG-16-JS model significantly reduces the number of parameters required for model training without a significant drop in the success rate. It solves the GPU memory requirements for training neural networks to a certain extent. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
BACKGROUND The ZF2001 vaccine, which contains a dimeric form of the receptor-binding domain ofsevere acute respiratory syndrome coronavirus 2 and aluminum hydroxide as an adjuvant, was shown to be safe, with an acceptable side-effect profile, and immuno-genie in adults in phase 1 and 2 clinical trials. METHODS We conducted a randomized, double-blind, placebo-controlled, phase 3 trial to in. vestigate the efficacy and confirm the safety of ZF2001. The trial was performed at 31 clinical centers across Uzbekistan, Indonesia, Pakistan, and Ecuador;an addi-tional center in China was included in the safety analysis only. Adult participants (218 years of age) were randomly assigned in a 1:1 ratio to receive a total of three 25-/Lg doses (30 days aparO of ZF2001 or placebo. The primary end point was the occurrence of symptomatic coronavirus disease 2019 (Covid-19), as confirmed on polymerase-chain-reaction assay, at least 7 days after receipt of the third dose. A key secondary efficacy end point was the occurrence of severe-to-critical Covid-19 (including Covid-19-related death) at least 7 days after receipt of the third dose. RESULTS Between December 12, 2020, and December 15, 2021, a total of28,873 participants received at least one dose of ZF2OO1 or placebo and were ineluded in the safety analysis;25,193 participants who had completed the three-dose regimen, for whom there were approximately 6 months of follow-up data, were included in the updated primary efficacy analysis that was conducted at the second data cutoff date of December 15, 2021. In the updated analysis, primary end-point cases were reported in 158 of 12,625 participants in the ZF2001 group and in 580 of 12,568 participants in the placebo group, for a vaccine efficacy of 75.7°/0 (95°6 confidence interval [CI], 71.0 to 79.8). Severe-to-critical Covid-19 occurred in 6 participants in the ZF2001 group and in 43 in the placebo group, for a vaccine efficacy of 87.6% (95% CI, 70.6 to 95.7);Covid-19-related death occurred in 2 and 12 participants, respectively, for a vaccine efficacy of 86.5% (95% CI, 38.9 to 98.5). The incidence of adverse events and serious adverse events was balanced in the two groups, and there were no vaccine-related deaths. Most adverse reactions (98.590) were of grade 1 or 2. CONCLUSIONS In a large cohort of adults, the ZF2001 vaccine was shown to be safe and effective against symptomatic and severe-to-critical Covid-19 for at least 6 months after full vaccination. (Funded by the National Science and Technology Major Project and others;ClinicalTrials.gov number, NCT04646590.). [ FROM AUTHOR] Copyright of New England Journal of Medicine is the property of New England Journal of Medicine and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
ABSTRACT
Since 2019, COVID-19 has seriously affected many industries of the economy. It is a major emergency risk event, which has caused a huge impact on all kinds of projects implemented by engineering enterprises. Nowadays, more and more engineering have introduced ecological concepts and achieved remarkable results in the fields of energy conservation, environmental protection, and renewable energy utilization. In the current global situation, how to improve the sustainable development of intelligent engineering has become a new problem. The paper explains the social responsibility connotation of intelligent engineering by using the framework proposed by ISO 26000. It puts forward that the expectations of employees, shareholders, communities, consumers, supply chains, governments, and other stakeholders should be fully taken into account in the whole process of the project. By analyzing the problems of intelligent engineering on social responsibility, it provides some suggestions from the seven core subjects of ISO 26000, such as organizational governance, human rights, labor practices, the environment, fair operating practices, consumer issues, and community involvement and development.