ABSTRACT
Online discussion of the ensuing pandemic exemplifies the extent and complexity of information required to understand human perception. Social media has proven to be a viable medium for identifying actionable data and analyzing public perception. As health sectors all over the world battled to obtain accurate information regarding COVID-19, this research focused on gauging public perceptions of the vaccine. The public reception of the vaccine can be determined by public perception. This study explores how to use machine learning to understand human perceptions in the context of the COVID-19 vaccine. Natural Language Processing (NLP) was employed to detect pro- and anti-vaccine tweets, while two machine learning classification models were used to study the patterns derived from the analysis. The study analyzed people's perceptions of the vaccine by presenting the results from a geographic region, while learning patterns that are likely to be associated with pro- or anti-vaccine perceptions. © 2022 IEEE Computer Society. All rights reserved.
ABSTRACT
It is necessary to ensure the quality of students' courses, especially practical courses, which is an important part of higher education, and plays a positive role in promoting and popularizing the improvement of innovation and entrepreneurship in the face of the non suspension of classes and schools under the COVID-19. This paper explores the mode of online and offline combined with ideological and political education mixed teaching reform in the course, in order to explore the educational functions and ideological and political elements of the course from the practical contents and objectives from the practical course of artificial intelligence foundation, explore the implementation methods and teaching concepts of ideological and political education in the course, so that students can better master and understand knowledge comprehensively, improve the results of students' ideological and moral education, and explore the reform mode which satisfy the requirements of talent training. © 2022 IEEE.
ABSTRACT
Purpose: Given the importance of spatial effects in improving the accuracy of hotel demand forecasting, this study aims to introduce price and online rating, two critical factors influencing hotel demand, as external variables into the model, and capture the spatial and temporal correlation of hotel demand within the region. Design/methodology/approach: For high practical implications, the authors conduct the case study in Xiamen, China, where the hotel industry is prosperous. Based on the daily demand data of 118 hotels before and during the COVID-19 period (from January to June 2019 and from January to June 2021), the authors evaluate the prediction performance of the proposed innovative model, that is, a deep learning-based model, incorporating graph convolutional networks (GCN) and gated recurrent units. Findings: The proposed model simultaneously predicts the daily demand of multiple hotels. It effectively captures the spatial-temporal characteristics of hotel demand. In addition, the features, price and online rating of competing hotels can further improve predictive performance. Meanwhile, the robustness of the model is verified by comparing the forecasting results for different periods (during and before the COVID-19 period). Practical implications: From a long-term management perspective, long-term observation of market competitors' rankings and price changes can facilitate timely adjustment of corresponding management measures, especially attention to extremely critical factors affecting forecast demand, such as price. While from a short-term operational perspective, short-term demand forecasting can greatly improve hotel operational efficiency, such as optimizing resource allocation and dynamically adjusting prices. The proposed model not only achieves short-term demand forecasting, but also greatly improves the forecasting accuracy by considering factors related to competitors in the same region. Originality/value: The originalities of the study are as follows. First, this study represents a pioneering attempt to incorporate demand, price and online rating of other hotels into the forecasting model. Second, integrated deep learning models based on GCN and gated recurrent unit complement existing predictive models using historical data in a methodological sense. © 2022, Emerald Publishing Limited.
ABSTRACT
To solve the problem of inaccurate entity extraction caused by low application efficiency and big data noise in telemedicine sensing data, a deep learning-based method for entity relationship extraction in telemedicine big data is proposed. By analyzing the distribution structure of the medical sensing big data, the fuzzy function of the distribution shape is calculated and the seed relationship set is transformed by the inverse Shearlet transform. Combined with the deep learning technology, the GMM-GAN data enhancement model is built, the interactive medical sensing big data features are obtained, the association rules are matched one by one, the noiseless medical sensing data are extracted in time sequence, the feature items with the highest similarity are obtained and used as the constraint to complete the feature entity relationship extraction of the medical sensing data. The experimental results show that the extracted similarity of entity relations is more than 70%, which can handle overly long and complex sentences in telemedicine information text;the extraction time is the shortest and the volatility is low.
ABSTRACT
Purpose Given the importance of spatial effects in improving the accuracy of hotel demand forecasting, this study aims to introduce price and online rating, two critical factors influencing hotel demand, as external variables into the model, and capture the spatial and temporal correlation of hotel demand within the region. Design/methodology/approach For high practical implications, the authors conduct the case study in Xiamen, China, where the hotel industry is prosperous. Based on the daily demand data of 118 hotels before and during the COVID-19 period (from January to June 2019 and from January to June 2021), the authors evaluate the prediction performance of the proposed innovative model, that is, a deep learning-based model, incorporating graph convolutional networks (GCN) and gated recurrent units. Findings The proposed model simultaneously predicts the daily demand of multiple hotels. It effectively captures the spatial-temporal characteristics of hotel demand. In addition, the features, price and online rating of competing hotels can further improve predictive performance. Meanwhile, the robustness of the model is verified by comparing the forecasting results for different periods (during and before the COVID-19 period). Practical implications From a long-term management perspective, long-term observation of market competitors' rankings and price changes can facilitate timely adjustment of corresponding management measures, especially attention to extremely critical factors affecting forecast demand, such as price. While from a short-term operational perspective, short-term demand forecasting can greatly improve hotel operational efficiency, such as optimizing resource allocation and dynamically adjusting prices. The proposed model not only achieves short-term demand forecasting, but also greatly improves the forecasting accuracy by considering factors related to competitors in the same region. Originality/value The originalities of the study are as follows. First, this study represents a pioneering attempt to incorporate demand, price and online rating of other hotels into the forecasting model. Second, integrated deep learning models based on GCN and gated recurrent unit complement existing predictive models using historical data in a methodological sense.
ABSTRACT
BACKGROUND: Oncolytic viruses are considered part of immunotherapy and have shown promise in preclinical experiments and clinical trials. Results from these studies have suggested that tumor microenvironment remodeling is required to achieve an effective response in solid tumors. Here, we assess the extent to which targeting specific mechanisms underlying the immunosuppressive tumor microenvironment optimizes viroimmunotherapy. METHODS: We used RNA-seq analyses to analyze the transcriptome, and validated the results using Q-PCR, flow cytometry, and immunofluorescence. Viral activity was analyzed by replication assays and viral titration. Kyn and Trp metabolite levels were quantified using liquid chromatography-mass spectrometry. Aryl hydrocarbon receptor (AhR) activation was analyzed by examination of promoter activity. Therapeutic efficacy was assessed by tumor histopathology and survival in syngeneic murine models of gliomas, including Indoleamine 2,3-dioxygenase (IDO)-/- mice. Flow cytometry was used for immunophenotyping and quantification of cell populations. Immune activation was examined in co-cultures of immune and cancer cells. T-cell depletion was used to identify the role played by specific cell populations. Rechallenge experiments were performed to identify the development of anti-tumor memory. RESULTS: Bulk RNA-seq analyses showed the activation of the immunosuppressive IDO-kynurenine-AhR circuitry in response to Delta-24-RGDOX infection of tumors. To overcome the effect of this pivotal pathway, we combined Delta-24-RGDOX with clinically relevant IDO inhibitors. The combination therapy increased the frequency of CD8+ T cells and decreased the rate of myeloid-derived suppressor cell and immunosupressive Treg tumor populations in animal models of solid tumors. Functional studies demonstrated that IDO-blockade-dependent activation of immune cells against tumor antigens could be reversed by the oncometabolite kynurenine. The concurrent targeting of the effectors and suppressors of the tumor immune landscape significantly prolonged the survival in animal models of orthotopic gliomas. CONCLUSIONS: Our data identified for the first time the in vivo role of IDO-dependent immunosuppressive pathways in the resistance of solid tumors to oncolytic adenoviruses. Specifically, the IDO-Kyn-AhR activity was responsible for the resurface of local immunosuppression and resistance to therapy, which was ablated through IDO inhibition. Our data indicate that combined molecular and immune therapy may improve outcomes in human gliomas and other cancers treated with virotherapy.
Subject(s)
Glioma , Oncolytic Viruses , Animals , CD8-Positive T-Lymphocytes/metabolism , Glioma/therapy , Humans , Indoleamine-Pyrrole 2,3,-Dioxygenase , Kynurenine/metabolism , Mice , Oncolytic Viruses/genetics , Oncolytic Viruses/metabolism , Synapses/metabolism , Tumor MicroenvironmentABSTRACT
Background: Travel restrictions during the COVID-19 epidemic in China have impacted on the daily life and antiretroviral therapy (ART) of people living with HIV, including men who have sex with men (MSM). As China enters a state of routine COVID-19 prevention and control, it is necessary to understand the conditions of ART interruption (ATI) among HIV-infected MSM during and after the lockdown period (23 January to 7 April 2020) to summarize experience on HIV treatment. Methods: A nationwide cross-sectional online survey was conducted among HIV-infected MSM in China in February 2021, using convenience sampling on the WeChat platform called Li Hui Shi Kong. We collected information during and around lockdown period, including socio-demographics, health behaviors such as physical exercise and alcohol drinking, ART maintenance, CD4 and viral load testing. Pearson's Chi-squared test was performed to compare those characteristics between participants who experienced ATI during the lockdown period and did not. Logistic regression analysis was conducted to assess the correlates of ATI. Results: A total of 1296 participants were included in the analysis. The median age was 29.3 years (interquartile range [IQR] 25.2-34.0). 40.9% (n=530) of them did not exercise regularly in the second half of 2019 and 62.3% (n=808) had alcohol drinking. During the lockdown period, 6.8% (n=88) reported ATI experience, and 49.5% (n=629) performed CD4 cell test. Among the participants who took the last CD4 test after the lockdown, more people had not experienced ATI (66.8%) compared to those had experienced ATI (38.6%). HIV-infected MSM using other ART regimen as temporary substitution were more unlikely to experience ATI, including free ART (adjusted odds ratio [aOR] 0.05, 95% confidence interval [CI] 0.02-0.11) and out-of-pocket ART (aOR 0.11, 95% CI 0.01-0.89), which is different from their previous prescription. Conclusion: COVID-restrictions did not result in significantly negative effects on ART maintenance among HIV-infected MSM in China. In order to reduce the negative impact on HIV-infected MSM, attention should be paid to conducting health behavior education, maintaining ART service and encouraging CD4 and viral load testing during and after public emergencies.
ABSTRACT
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature of blurred boundaries, the supervised segmentation methods usually suffer from annotation biases. To support unbiased lesion localisation and to minimise the labelling costs, we propose a data-driven framework supervised by only image level labels. The framework can explicitly separate potential lesions from original images, with the help of an generative adversarial network and a lesion-specific decoder. Experiments on two COVID-19 datasets demonstrates the effectiveness of the proposed framework and its superior performance to several existing methods.
ABSTRACT
We investigated the moderating role of employment stress in the relationship between proactive personality and career decision-making self-efficacy among recent Chinese graduates during the COVID-19 pandemic. The main results are as follows: (a) proactive personality positively predicted career decision-making self-efficacy, (b) employment stress was negatively related to proactive personality and career decision-making self-efficacy, and (c) employment stress significantly and negatively moderated the effect of proactive personality on career decision-making self-efficacy, meaning that the moderating effect was stronger at a lower level of employment stress. The results indicate that students graduating during the COVID-19 pandemic are more prone to suffering from complex career decision-making processes exacerbated by a challenging and changing labor market. Our findings suggest that graduates should secure flexible employment options and that officials, staff, and managers in governments, universities, and industries should work together to enhance graduates' career decision-making self-efficacy and assist them in achieving their early career aspirations by alleviating internal and external employment pressure. © 2021 Scientific Journal Publishers Limited. All Rights Reserved.
ABSTRACT
Recently, due to the outbreak of the COVID-19 epidemic in the world, wearing face masks has become a trend, which brings difficulties to the traditional face recognition technologies that do not actively focus on the upper part of the face. This paper proposes a novel method for masked face recognition based on attention mechanism and FaceX-Zoo (an open-source method of JD.COM). In order to make the module focus on the regions around the eyes, we integrated the CBAM (Convolutional Block Attention Module) attention mechanism into ResNet50 and MobileFaceNet network. Furthermore, the FaceX-Zoo method was used to generate masked face images to improve the module performance. Experiment results show that the proposed approach can improve the performance of masked face recognition compared with competitive approaches. © 2021 IEEE.
ABSTRACT
Background: The COVID-19 pandemic is associated with delayed revascularization and worse clinical outcomes for patients with ST-Elevation MI (STEMI). The purpose of this study was to evaluate whether a comprehensive STEMI protocol (CSP), which improved door-to-balloon times (D2BT) and mortality prior to the pandemic, mitigated the pandemic's negative effect on STEMI care and outcomes. Methods: We performed a prospective, single-center, registry-based study of 433 patients who received PCI for STEMI though an established CSP. We compared D2BT and in-hospital mortality of the period immediately prior to the pandemic (control period;1/1/19 -3/14/20, N=291) with the period from 3/15/20 to 12/31/20 (study period, N=142), in-line with the declaration of a state of emergency by the state of Ohio. Results: Between control and study period, patients were similar in regards to age (61.2 +/- 12.0 yrs vs. 61.7 +/-13.2 yrs), female sex (32.3% vs 30.3%), nonwhite race (30% vs 26%), smoking status, BMI (30.4 +/- 8.9 vs 29.9 +/- 6.3), and other comorbidities. There was no significant difference in % meeting D2BT goals for STEMI (<=90 minutes for ED and in-hospital, <=120 minutes for hospital transfer patients) during control and study periods (79.0% v 78.9%, p = 0.97). When stratified by STEMI presenting location, there was no significant difference between control and study period D2BT for patients presenting in primary ED (48 min [IQR 36-66] vs 60 min [IQR 42-73], p = 0.09), as hospital transfers (96 min [IQR 79-119] vs 95 min [IQR 80-112], p = 0.86), or from in-hospital locations (95 min [IQR 80-112] vs 95.8 min [IQR 52-120], p = 0.50). There was no significant difference in in-hospital mortality between the control and study periods (4.5% and 2.1%, p = 0.22). Conclusions: Despite the profound effect of pandemic on overall health care operations, there was little overall change in STEMI process and outcome metrics within a high reliability CSP.
ABSTRACT
Objective: The objective of the study was to compare the application effects of in-vial exhaust method and conventional exhaust method in the process of coronavirus disease 2019 vaccine injection. Materials and Methods: Using convenient sampling method, 102 vaccines were selected as experiment group during the process of vaccine injection, and the in-vial exhaust method was used. One hundred and five vaccines were selected as the control group and the conventional exhaust method was adopted. The incidence of vaccine solution spillage and exhausting time in the two groups during exhaust were observed. Results: The incidence of solution spillage in the experiment group was lower than that in the control group (0 vs. 6.67%, P < 0.05). The exhausting time of the experiment group was shorter than that of the control group ([15.12 ± 4.43] s vs. [22.74 ± 6.53] s, P < 0.05). Conclusion: Implementing the in-vial exhaust method in the vaccine injection can effectively reduce the incidence of solution spillage, reduce nucleic acid contamination, and ensure that the vaccine is injected at the prescribed dose. Moreover, the operation is simple and easy, which improves the nurse's vaccination efficiency, and has a higher promotion and application value. © 2021 Journal of Integrative Nursing ;Published by Wolters Kluwer - Medknow.
ABSTRACT
The coronavirus virus (COVID-19) epidemic has swept the world, with the World Health Organization defining it as a pandemic on March 11. This in turn has affected the approaches and methods used in education throughout the world. According to United Nations report, by the time of mid-April 2020, 94% of learners in more than 200 countries around the world have been affected, and 1.58 billion students from pre-school to higher education are affected. In response to increased learning needs regarding infection prevention, the Ministry of Education has also provided cloud educational resources and private online learning resources, platforms, and tools to schools at all levels to encourage teachers and students to make effective use of digital resources. Although the government provides abundant teaching resources, the implementation of distance teaching in college physical education still faced with many problems, such as the shortage of course resources, the lack of information literacy of teachers, the difficulty in implementing conventional teaching plans online, the limited conditions for students to exercise at home, and the doubts about online physical education. Therefore, this study proposes a new teaching method, and studies, analyzes and discusses this method. The method of experimental design was adopted in this study to divide the students into two groups: blended learning group (synchronous and asynchronous) and single type learning group (synchronous). The results show that blended learning students perform better than single type learning students in all these aspects, which proves the practicability and effectiveness of the proposed method. © The Author(s) 2021.
ABSTRACT
Coronavirus disease 2019 (COVID-19) has resulted in an ongoing pandemic. Since COVID-19 spreads mainly via close contact among people, social distancing has become an effective manner to slow down the spread. However, completely forbidding close contact can also lead to unacceptable damage to the society. Thus, a system that can effectively monitor people's social distance and generate corresponding alerts when a high infection probability is detected is in urgent need. In this paper, we propose SmartDistance, a smartphone based software framework that monitors people's interaction in an effective manner, and generates a reminder whenever the infection probability is high. Specifically, SmartDistance dynamically senses both the relative distance and orientation during social interaction with a well-designed relative positioning system. In addition, it recognizes different events (e.g., speaking, coughing) and determines the infection space through a droplet transmission model. With event recognition and relative positioning, SmartDistance effectively detects risky social interaction, generates an alert immediately, and records the relevant data for close contact reporting. We prototype SmartDistance on different Android smartphones, and the evaluation shows it reduces the false positive rate from 33% to 1% and the false negative rate from 5% to 3% in infection risk detection.
ABSTRACT
Mask wearing has been considered as an effective measure to prevent the spread of COVID-19 during the current pandemic. However, most advanced face recognition approaches are not adequate for masked face recognition, particularly in dealing with the issue of training through the datasets covering only a limited number of images with ground-truth labels. In this work, we propose to learn from the large scale of web images and corresponding tags without any manual annotations along with limited fully annotated datasets. In particular, inspired by the recent success of webly supervised learning in deep neural networks, we capitalize on readily-available web images with noisy annotations to learn a robust representation for masked faces. Besides, except for the conventional spatial representation learning, we propose to leverage the power of frequency domain to capture the local representative information of unoccluded facial parts. This approach learns robust feature embeddings derived from our feature fusion architecture to make joint and full use of information from both spatial and frequency domains. Experimental results on seven benchmarks show that the proposed approach significantly improves the performance compared with other state-of-theart methods.
ABSTRACT
The global novel coronavirus COVID-19 has spread far beyond any previous cases in the world, due to its high infect ability, robots are in high demand all over the world, which can help hospital services, protect the health and safety of front-line medical workers. This paper investigates the use of an autonomous service robot in an indoor complex environment, such as a hospital ward or a retirement home. The research is based on the method of fusing lidar and image information to identify, locate, and track the human body in the indoor environment. Use lidar SLAM to obtain the pose of pedestrians in the environment, and incorporate the predicted pedestrian trajectory into the planning constraints of the navigation algorithm to ensure that human behavior intentions are respected, and verify the humanized navigation of the mobile robot in the human-machine inclusive indoor environment through online simulation and experimental platform. The main advantages of the design of this mobile robot are that it can improve the friendliness of humanmachine integration in order to do better serves in public environments such as medical institutions.
ABSTRACT
Beginning at the end of 2019, corona virus disease 2019(COVID-19) caused by sevare acute respiratory syndrome coronavirus(SARS-CoV-2) appeared in Wuhan, China, and spread rapidly across the country. Prior to this, there had been two outbreaks in the world that caused serious consequences by different coronaviruses: severe acute respiratory syndrome coronavirus (SARS-CoV) and Middle East respiratory syndrome coronavirus (MERS-CoV). This article introduces the structure and classification of coronaviruses, discusses the origin, virological characteristics, and epidemiological overview of three coronaviruses-SARS-CoV, MERS-CoV, and SARS-CoV-2, and reviews the drugs that are currently on the market and are being developed to treat coronavirus infections, in order to explain the characteristics of coronavirus and provide new ideas for the prevention and control of 2019-nCoV and new coronavirus.