Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 23
Filter
1.
Journal of Investigative Dermatology ; 142(8):S59, 2022.
Article in English | EMBASE | ID: covidwho-1956218

ABSTRACT

The COVID-19 pandemic has accelerated the adoption of telemedicine. However, current tools pose substantial barriers for older adults and those with low digital literacy. By implementing user-centered design, we developed a digital tool, Dermatology for Older Adults (DORA), for home-based monitoring of skin disease, specifically designed for older adults. DORA is a virtual assistant based on REDCap and Twilio APIs that automates image and symptom collection and allows communication between patients and the research team. We evaluated the feasibility, usability, patient compliance, retention, and clinical utility of DORA. Eligibility criteria included patients >70 years with any skin disease, access to a smartphone, and no cognitive impairment. We recruited 62 patients aged 70-94 (mean age 77), 39% female, 81% white from Stanford’s Dermatology Clinic from August-December 2021. We asked patients to send weekly photos and answer a questionnaire of a single skin lesion for 4 weeks, then monthly for 4 months. We measured response time, photo quality, and participant satisfaction using mHealth app usability questionnaire (MAUQ). The median response time was 1.4 days (IQR 0.6-3.4). Four participants dropped out. 83% completed photo submission requests (48% at initial request, 19% after 1st reminder and 16% after 2nd reminder). 80% of all questionnaires requested (131 of 163) were completed. Four dermatology clinicians evaluated the quality of the first 88 images and reported good confidence in triaging skin diseases. MAUQ scores were high for ease of use (5.6 SD1.3), interface satisfaction (5.5 SD1.3), and usefulness (5.2 SD1.3). Patients were consistently able to use DORA to submit photos and symptoms and reported high usability and satisfaction. Patient retention was high, and clinicians felt confident making triage recommendations based on DORA images. This approach can be used in other settings where digital literacy barriers and unequal access to dermatologists contribute to healthcare disparities.

2.
Shipin Kexue/Food Science ; 43(5):346-355, 2022.
Article in Chinese | Scopus | ID: covidwho-1847651

ABSTRACT

As an important immuneoactive component in eggs, yolk immunoglobulin (IgY) shows great competitiveness in research and production due to its good stability, high safety, low cost, easy availability, strong immune activity, and no drug resistance. This article highlights the significant advantages of IgY as a good antibiotic substitute in the prevention and treatment of viral and bacterial diseases. Also, IgY has great potential in the regulation of nutrient metabolism balance, intestinal microflora and immune homeostasis by affecting key rate-limiting enzymes, and relevant receptors and inflammatory factors specifically. Proper diet and targeted delivery of foodborne IgY may be a new perspective on inflammation regulation, disease control, nutritional balance or homeostasis, and oral microencapsulated IgY is expected to be a new approach against increasing public health emergencies (such as COVID-19 pandemic). © 2022, China Food Publishing Company. All right reserved.

3.
American Journal of Translational Research ; 14(3):2063-2072, 2022.
Article in English | EMBASE | ID: covidwho-1777100

ABSTRACT

We present a study protocol designed to test the safety and efficacy of the 2019 coronavirus disease (COVID-19) vaccine in patients with major psychotic disease. A secondary objective is to investigate optional vaccination methods for these patients. In a self-experiment, a Chinese psychiatrist examined the safety and efficacy of the COVID-19 vaccine under clinical use of typical antipsychotic agents and sedatives (olanzapine, duloxetine, and diazepam). For patients with extremely drug-resistant conditions, the safety of the COVID-19 vaccine under electroconvulsive therapy was also investigated. The entire study process was recorded on high-definition video. This clinical study protocol is, to our knowledge, the first of its kind. Our findings will shed new light on the protection of patients with psychotic diseases from COVID-19 infection.

4.
Ieee Transactions on Computational Social Systems ; : 12, 2022.
Article in English | Web of Science | ID: covidwho-1714076

ABSTRACT

COVID-19 has spread all over the world, accounting for countless death and enormous economic loss. Since the World Health Organization (WHO) declared COVID-19 as a pandemic, governments from different countries have made various policies to prevent the pandemic from becoming worse. However, civilian reactions to the pandemic vary when they face similar situations. This behavioral variation creates a challenge when it comes to policy-making. Such differences are generally implicit, hidden in ones' social lives. As a result, it is challenging to analyze such differences when the governments make policies. In this work, we investigate social media posts on Twitter and Weibo in order to effectively explore the difference in reactions across various countries, with the aim to understand national differences. To this end, we employ natural language processing (NLP) methods and Linguistic Inquiry and Word Count (LIWC) tools to process six languages in different countries, including the USA, Germany, France, Italy, the U.K., and China. We provide a comprehensive analysis of public reaction differences from the emotional perspective. Our findings verify that the reactions vary noticeably among various countries for some policies. Therefore, sentiment analysis can significantly influence policy-making. Our work sheds light on the mechanism of detecting the reaction differences in various countries, which can be utilized to conduct effective communication and make appropriate policy decisions.

5.
Embase;
Preprint in English | EMBASE | ID: ppcovidwho-326937

ABSTRACT

SARS-CoV-2 continued to spread globally along with different variants. Here, we systemically analyzed viral infectivity and immune-resistance of SARS-CoV-2 variants to explore the underlying rationale of viral mutagenesis. We found that the Beta variant harbors both high infectivity and strong immune resistance, while the Delta variant is the most infectious with only a mild immune-escape ability. Remarkably, the Omicron variant is even more immune-resistant than the Beta variant, but its infectivity increases only in Vero E6 cells implying a probable preference for the endocytic pathway. A comprehensive analysis revealed that SARS-CoV-2 spike protein evolved into distinct evolutionary paths of either high infectivity plus low immune resistance or low infectivity plus high immune resistance, resulting in a narrow spectrum of the current single-strain vaccine. In light of these findings and the phylogenetic analysis of 2674 SARS-CoV-2 S-protein sequences, we generated a consensus antigen (S6) taking the most frequent mutations as a pan-vaccine against heterogeneous variants. As compared to the ancestry SWT vaccine with significantly declined neutralizations to emerging variants, the S6 vaccine elicits broadly neutralizing antibodies and full protections to a wide range of variants. Our work highlights the importance and feasibility of a universal vaccine strategy to fight against antigen drift of SARS-CoV-2.

6.
CCS Chemistry ; 4(1):112-121, 2022.
Article in English | Scopus | ID: covidwho-1644130

ABSTRACT

Currently, there is no effective antiviral medication for coronavirus disease 2019 (COVID-19) and the knowledge on the potential therapeutic target is in great need. Guided by a time-course transmission electron microscope (TEM) imaging, we analyzed early phosphorylation dynamics within the first 15 min during severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) viral entry. Based on alterations in the phosphorylation events, we found that kinase activities such as protein kinase C (PKC), interleukin-1 receptor-associated kinase 4 (IRAK4), MAP/microtubule affinity-regulating kinase 3 (MARK3), and TANK-binding kinase 1 (TBK1) were affected within 15 min of infection. Application of the corresponding kinase inhibitors of PKC, IRAK4, and p38 showed significant inhibition of SARS-CoV-2 replication. Additionally, proinflammatory cytokine production was reduced by applying PKC and p38 inhibitors. By an acquisition of a combined image data using positiveand negative-sense RNA probes, as well as pseudovirus entry assay, we demonstrated that PKC contributed to viral entry into the host cell, and therefore, could be a potential COVID-19 therapeutic target. © 2022 Chinese Chemical Society. All right reserved.

7.
Lecture Notes on Data Engineering and Communications Technologies ; 103:1007-1013, 2022.
Article in English | Scopus | ID: covidwho-1620222

ABSTRACT

This article studies the customer satisfaction of online shopping, express delivery, airline service, online travel, express hotel, commercial bank, auto insurance and mobile communication in China in the context of COVID-19 epidemic. The research collects customer satisfaction data through questionnaire surveys and have a total of 13,000 valid samples. According to the survey, consumers are relatively satisfied with customer satisfaction in China's service industry. Among the eight industries studied, online shopping and express delivery have higher customer satisfaction scores, and mobile communications have lower score. The improvement of perceived quality and brand image will help to better improve customer satisfaction, reflecting that consumer satisfaction is more affected by subjective feelings and brand. In addition, this article also collected consumer complaints, brand value and other data, through comprehensive analysis of multi-dimensional data, it analyzes the current quality of China's service industry and provides opinions and suggestions for policy formulation. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

8.
Gaodeng Xuexiao Huaxue Xuebao/Chemical Journal of Chinese Universities ; 42(11):3509-3518, 2021.
Article in English | Scopus | ID: covidwho-1524547

ABSTRACT

Rapid detection of body fluid severe acute respiratory syndrome coronavirus 2(SARS-CoV-2) antibody is an effective strategy for infection therapeutic effect of coronavirus disease(COVID-19). Most detection methods require relatively large equipment, which limited their on-site application. Lateral flow immunoassay(LFIA) can be used to qualitative antibody detection based on the aggregation of gold nanoparticles (Au NPs), which exhibits just one-color change and cannot realize rapid quantitative detection without the help of additional equipment. In this study, a high-resolution multicolor colorimetric strategy was developed and applied to assessing antibody concentration at a glance based on etching of gold nanorods(Au NRs). Firstly, SARS-CoV-2 recombinant antigen was immobilized on the surface of the 96-wells. Then, horseradish peroxidase(HRP)-labeled second antibody combined with antibody to form an antigen-antibody-secondary antibody complex on the well surface, which has direct relationship with antibody concentration in the sample and can be used to oxidize 3, 3', 5, 5'-tetramethylbenzidine(TMB) to form TMB2+ at the presence of HRP. The generation of TMB2+ efficiently etch Au NRs to produce multicolor solution. The etching result in vivid color changes in the system has a relationship with the amount of SARS-CoV-2 IgM antibody. Under the optimal conditions, the proposed strategy exhibited a linear response in the 5.00―200 IU concentration range, and a detection limit of 1.29 IU for SARS-CoV-2 IgM antibody, with high sensitivity and specificity. This assay is prospective for the on-site semi-quantitative visual detection of SARS-CoV-2 IgM antibody concentration in the COVID-19 therapeutic process. © 2021, Editorial Department of Chem. J. Chinese Universities. All right reserved.

9.
IEEE Transactions on Industrial Informatics ; 2021.
Article in English | Scopus | ID: covidwho-1515173

ABSTRACT

As the coronavirus disease 2019 (COVID-19) spreads around the world, industrial automated medical diagnosis systems have been developed, which complete a large amount of medical diagnosis work through computed tomography (CT) images. In these systems, how to quickly store and transmit such a large amount of CT image information has important research significance. In this paper, a more targeted COVID-19 chest CT image codec is proposed to make image data not only occupy less space but also have higher image quality. First, the bilateral lung contours are extracted to calculate the position information of the region of interest (ROI). Then, a CT image is classified into four types of non-uniform image blocks according to the characteristics of COVID-19 chest CT images and ROI position information. Next, a series of new transformations are proposed for more efficient transform coding. Finally, a flexible quantization strategy is proposed for the adaptive quantization part. In the experiments, the proposed method is superior to some existing methods with similar computational complexity. At the same bit rate, it significantly improves the image quality. This means that chest CT images can still be used for disease diagnosis while taking up less space. In addition, because of the low computational complexity of the proposed method, it can be more easily embedded into the CT equipment with low computational power. IEEE

10.
Journal of Chinese Mass Spectrometry Society ; 42(5):563-584, 2021.
Article in Chinese | Scopus | ID: covidwho-1449174

ABSTRACT

COVID-19 has caused a huge health crisis and incalculable damage worldwide. Emerging immune escaping mutants of the virus suggests that SARS-CoV-2 may be persistent in human society like the flu virus and become a long-lasting health threat. The control of SARS-CoV-2 transmission and the development of an effective treatment are imminent. Therefore, it is imperative to find appropriate biomarkers to indicate pathological and physiological. Proteins are performers of life functions and their abundance and modification status can directly reflect the immune status. Post-translational modifications such as glycosylation and phosphorylation have a great impact on the regulation of protein functions. In the studies of SARS, Zika, and H1N1, post-translational modified proteins have shown to be reliable biomarkers. In recent years, mass spectrometry-based proteomics has made great progress due to the development of mass spectrometry technology. A review of research strategies for mass spectrometry-based biomarkers, especially in the application of protein post-translational modifications, is important for the victory of human beings fighting the Covid-19 epidemic. This review summarized the current progress of mass spectrometry-based studies on the PTM status of SARS-CoV-2 viral proteins, particularly in glycosylation and phosphorylation aspect. The challenge and prospect of the application of mass spectrometry in this particular research area were outlined. © 2021, Editorial Board of Journal of Chinese Mass Spectrometry Society. All right reserved.

11.
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2021 ; 12978 LNAI:319-334, 2021.
Article in English | Scopus | ID: covidwho-1446044

ABSTRACT

Modeling and predicting human mobility are of great significance to various application scenarios such as intelligent transportation system, crowd management, and disaster response. In particular, in a severe pandemic situation like COVID-19, human movements among different regions are taken as the most important point for understanding and forecasting the epidemic spread in a country. Thus, in this study, we collect big human GPS trajectory data covering the total 47 prefectures of Japan and model the daily human movements between each pair of prefectures with time-series Origin-Destination (OD) matrix. Then, given the historical observations from past days, we predict the countrywide OD matrices for the future one or more weeks by proposing a novel deep learning model called Origin-Destination Convolutional Recurrent Network (ODCRN). It integrates the recurrent and 2-dimensional graph convolutional components to deal with the highly complex spatiotemporal dependencies in sequential OD matrices. Experiment results over the entire COVID-19 period demonstrate the superiority of our proposed methodology over existing OD prediction models. Last, we apply the predicted countrywide OD matrices to the SEIR model, one of the most classic and widely used epidemic simulation model, to forecast the COVID-19 infection numbers for the entire Japan. The simulation results also demonstrate the high reliability and applicability of our countrywide OD prediction model for a pandemic scenario like COVID-19. © 2021, Springer Nature Switzerland AG.

12.
Ieee Transactions on Industrial Informatics ; 17(11):7456-7467, 2021.
Article in English | Web of Science | ID: covidwho-1365029

ABSTRACT

Digital image feature recognition is significant to industrial information applications, such as bioengineering, medical diagnosis, and machinery industry. In order to supply an effective and reasonable technology of the severity assessment mission of coronavirus disease (COVID-19), in this article, we propose a new method that identifies rich features of lung infections from a chest computed tomography (CT) image, and then assesses the severity of COVID-19 based on the extracted features. First, in a chest CT image, the lung contours are corrected for the segmentation of bilateral lungs. Then, the lung contours and areas are obtained from the lung regions. Next, the coarseness, contrast, roughness, and entropy texture features are extracted to confirm the COVID-19 infected regions, and then the lesion contours are extracted from the infected regions. Finally, the texture features and V-descriptors are fused as an assessment descriptor for the COVID-19 severity estimation. In the experiments, we show the feature extraction and lung lesion segmentation results based on some typical COVID-19 infected CT images. In the lesion contour reconstruction experiments, the performance of V-descriptors is compared with some different methods, and various feature scores indicate that the proposed assessment descriptor reflects the infected ratio and the density feature of the lesions well, which can estimate the severity of COVID-19 infection more accurately.

13.
2021 5th International Conference on Management Engineering, Software Engineering and Service Sciences, ICMSS 2021 ; : 143-147, 2021.
Article in English | Scopus | ID: covidwho-1350056

ABSTRACT

Small and Medium-sized Enterprises (SMEs) play significant roles in the development of the Chinese Economy Nowadays. However, SMEs still face many financing difficulties. Moreover, the explosion of the COVID-19 epidemic makes their living environment worse. Based on this, firstly, we collect the panel data from the first half of 2018 to the first half of 2020 of 1531 SMEs;Second, use the DEA-Malmquist model to calculate the financing efficiency of those SMEs;Then, analyze the influence of the COVID-19 epidemic situation on the finance for SMEs according to various industries. It can be revealed that the financing efficiency of SMEs tends to down on the whole. Among them, the financing efficiency of the industries like wholesale-retail trade, the manufacturing industry declined the most. From the perspective of the internal construction of the financing efficiency, the scale efficiency tends to be stable, which shows the good effect of the policy of supporting the loan;The decrease in the pure technical efficiency is the main reason behind the decrease in the financing efficiency. Finally, this paper puts forward suggestions to enhance the financing of SMEs considering the influence of the COVID-19 epidemic situation. © 2021 ACM.

14.
2021 5th International Conference on Management Engineering, Software Engineering and Service Sciences, ICMSS 2021 ; : 125-131, 2021.
Article in English | Scopus | ID: covidwho-1350055

ABSTRACT

The government creditability crisis, which is characterized as an event of high sensitivity and easy-To-explosion in terms of information, can induce large-scale network public opinion and consequently impair social stability. This is especially the case during the COVID-19 pandemic. This study aims to elucidate the rules underlying the network public opinion diffusion of COIVD-19 triggered government credibility crisis event and the corresponding countermeasures. A system dynamics model is established to formulate and simulate the interactions of four entities, that is, event per see, the netizens, the media, and the government, involved in the "Dr. Li Wenliang event"and their joint effects in the crisis evolution, shedding on the priority of influencing factors in different phases. The results indicate that the network public opinion follows the rule of "latency-outbreak-rise-fade". The sensitivity and explosiveness of the incident, the intensification of netizens, the public opinion leader effect, and the attention of the media play critical roles in network public opinion diffusion. Media's attention and netizen's intensification are the main influencing factors during the stage of public opinion explosion and waning period, respectively. The degree of government information disclosure and the early warning capability significantly alleviate the network public opinion diffusion. This study offers insight for government management in response to creditability crisis events during a special time. © 2021 ACM.

15.
Epidemiology and Infection ; 2021.
Article in English | EMBASE | ID: covidwho-1347908

ABSTRACT

From January 24, 2020 to May 18, 2020, Chaoshan took measures to limit the spread of COVID-19, such as restricting public gatherings, wearing masks, and suspending classes. We explored the effects of these measures on the pathogen spectrum of pediatric respiratory tract infections in Chaoshan. Pharyngeal swab samples were collected from 4075 children hospitalized for respiratory tract infection before (May-December 2019) and after (January-August 2020) the COVID-19 outbreak. We used liquid chip technology to analyze 14 respiratory pathogens. The data were used to explore between-group differences, age-related differences, and seasonal variations in respiratory pathogens. The number of cases in the outbreak group (1222) was 42.8% of that in the pre-outbreak group (2853). Virus-detection rates were similar in the outbreak (48.3%, 590/1222) and pre-outbreak groups (51.5%, 1468/2853;Χ2= 3.446, P = 0.065), while the bacteria-detection rate was significantly lower in the outbreak group (26.2%, 320/1222) than in the pre-outbreak group (44.1%, 1258/2853;Χ2= 115.621, P < 0.05). With increasing age, the proportions of respiratory syncytial virus (RSV) and cytomegalovirus (CMV) infections decreased, while those of Mycoplasma pneumoniae (MP), and adenovirus (ADV) infections increased. Streptococcus pneumoniae (SP), CMV, and rhinovirus infections peaked in autumn and winter, while RSV infections peaked in summer and winter. We found that the proportion of virus-only detection decreased with age, while the proportion of bacteria-only detection increased with age (Table 2). Anti-COVID-19 measures significantly reduced the number of pediatric hospitalizations for respiratory tract infections, significantly altered the pathogen spectrum of such infections, and decreased the overall detection rates of 14 common respiratory pathogens. The proportion of bacterial, but not viral, infections decreased.

16.
Letters in Drug Design & Discovery ; 18(5):429-435, 2021.
Article in English | Web of Science | ID: covidwho-1332066

ABSTRACT

Background: Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a novel member of the genus betacoronavirus in the Coronaviridae family. It has been identified as the causative agent of coronavirus disease 2019 (COVID-19), spreading rapidly in Asia, America and Europe. Like some other RNA viruses, RNA replication and transcription of SARS-CoV-2 rely on its RNA-dependent RNA polymerase (RdRP), which is a therapeutic target of clinical importance. Crystal structure of SARS-CoV-2 was solved recently (PDB ID 6M71) with some missing residues. Objective: We used SARS-CoV-2 RdRP as a target protein to screen for possible chemical molecules with potential anti-viral effects. Methods: Here we modelled the missing residues 896-905 via homology modelling and then analysed the interactions of Hepatitis C virus allosteric non-nucleoside inhibitors (NNIs) in the reported NNIs binding sites in SARS-CoV-2 RdRP. Results: We found that MK-3281, filibuvir, setrobuvir and dasabuvir might be able to inhibit SARS-CoV-2 RdRP based on their binding affinities in the respective binding sites. Conclusion: Further in vitro and in vivo experimental research will be carried out to evaluate their effectiveness in COVID-19 treatment in the near future.

17.
Academic Journal of Second Military Medical University ; 42(5):527-533, 2021.
Article in Chinese | EMBASE | ID: covidwho-1270303

ABSTRACT

Objective To investigate the insomnia status and the related influencing factors of clinical nurses fighting against coronavirus disease 2019 (COVID-19) in Wuhan, so as to provide references for targeted psychological intervention during the prevention and control of the COVID-19 epidemic. Methods Convenience sampling method was conducted among clinical nurses fighting against COVID-19 in the Zhongnan Hospital of Wuhan University from Mar. 3 to 7, 2020. General information questionnaire, Athens insomnia scale (AIS) and patient health questionnaire (PHQ-9) were used, and multivariate linear regression analysis was conducted to analyze the influencing factors of insomnia in clinical nurses fighting against COVID-19. Results A total of 521 questionnaires were collected, including 504 valid ones, with an effective rate of 96.74%. The AIS score was 6 (3, 9), of which 352 (69.84%) had sleep disorder;the PHQ-9 score was 6 (2, 9), of which 292 (57.94%) had different degrees of depression. Professional title, total working time at epidemic frontline, whether the direct relatives diagnosed as COVID-19 or not, fear of the COVID-19 epidemic and depression level were included in the regression equation (all P<0.05), which explained 56.2% of the total variation of insomnia in clinical nurses fighting against COVID-19. Conclusion Insomnia is common among clinical nurses fighting against COVID-19 in Wuhan, and the related influencing factors are complex. Nursing administrators should pay attention to the insomnia status of clinical nurses fighting against COVID-19, and all-round and effective interventions should be carried out in time, so as to improve the sleep quality of nurses.

18.
Lect. Notes Comput. Sci. ; 12672 LNAI:544-555, 2021.
Article in English | Scopus | ID: covidwho-1212814

ABSTRACT

With the influence of novel coronavirus, wearing masks is becoming more and more important. If computer vision system is used in public places to detect whether a pedestrian is wearing a mask, it will improve the efficiency of social operation. Therefore, a new mask recognition algorithm based on improved yolov3 is proposed. Firstly, the dataset is acquired through network video;secondly, the dataset is preprocessed;finally, a new network model is proposed and the activation function of YOLOv3 is changed. The average accuracy of the improved YOLOv3 algorithm is 83.79%. This method is 1.18% higher than the original YOLOv3. © 2021, Springer Nature Switzerland AG.

19.
Medical Journal of Wuhan University ; 42(3):373-378, 2021.
Article in Chinese | Scopus | ID: covidwho-1208879

ABSTRACT

Objective: To explore the depression status and its influencing factors of front-line nurses in a COVID-19 hospital in Wuhan during the period of prevention and control. Methods: 521 front-line nurses in a hospital in Wuhan during the epidemic of COVID-19 were selected for the cross-sectional survey study. The general data, the PHQ-9 depression screening scale, and the perceived stress scale were used to assess their mental status. Results: The average depression score of the front-line nurses was 6.49±5.40, among which 57.94% of them were more than 5 point, the average score was 10.12±4.17. Multiple stepwise regression analysis indicated that gender, average sleep time per night, frequency of regular meals per week, negative events experience, fear of epidemic, and perceived stress level were independent factors for depressive symptoms of nurses. Conclusion: The depression symptoms of front-line nurses are common in the work against COVID-19. The government and the medical departments should formulate and adopt effective strategies to prevent psychological stress, and to promote the mental health of front-line nurses. © 2021, Editorial Board of Medical Journal of Wuhan University. All right reserved.

20.
Tsinghua Science and Technology ; 26(5):759-771, 2021.
Article in English | Scopus | ID: covidwho-1208643

ABSTRACT

The novel coronavirus, COVID-19, has caused a crisis that affects all segments of the population. As the knowledge and understanding of COVID-19 evolve, an appropriate response plan for this pandemic is considered one of the most effective methods for controlling the spread of the virus. Recent studies indicate that a city Digital Twin (DT) is beneficial for tackling this health crisis, because it can construct a virtual replica to simulate factors, such as climate conditions, response policies, and people's trajectories, to help plan efficient and inclusive decisions. However, a city DTsystem relies on long-term and high-quality data collection to make appropriate decisions, limiting its advantages when facing urgent crises, such as the COVID-19 pandemic. Federated Learning (FL), in which all clients can learn a shared model while retaining all training data locally, emerges as a promising solution for accumulating the insights from multiple data sources efficiently Furthermore, the enhanced privacy protection settings removing the privacy barriers lie in this collaboration. In this work, we propose a framework that fused city DT with FL to achieve a novel collaborative paradigm that allows multiple city DTs to share the local strategy and status quickly. In particular, an FL central server manages the local updates of multiple collaborators (city DTs), providing a global model that is trained in multiple iterations at different city DT systems until the model gains the correlations between various response plans and infection trends. This approach means a collaborative city DT paradigm fused with FL techniques can obtain knowledge and patterns from multiple DTs and eventually establish a 'global view' of city crisis management. Meanwhile, it also helps improve each city's DT by consolidating other DT's data without violating privacy rules. In this paper, we use the COVID-19 pandemic as the use case of the proposed framework. The experimental results on a real dataset with various response plans validate our proposed solution and demonstrate its superior performance. ©2021 Tsinghua University Press. © 2021 Tsinghua University Press. All rights reserved.

SELECTION OF CITATIONS
SEARCH DETAIL