Implementation and Application of Large-Scale Drug Virtual Screening

The molecular docking-based virtual screening technique evaluates the binding abilities between multiple ligand compounds and receptors to screen for the active compounds. In the context of the global spread of the COVID-19 pandemic, large-scale and rapid drug virtual screening is crucial for identifying potential drug molecules from massive datasets of ligand structures. The powerful computing power of supercomputer provides hardware guarantee for drug virtual screening, but the super large-scale drug virtual screening still faces many challenges that affects the effective execution of the calculation. Based on the analysis of the challenges, this paper proposes a centralized task distribution scheme with a central database, and designs a multi-level task distribution framework. The challenges are effectively solved through multi-level intelligent scheduling, multi-level compression processing of massive small molecule files, dynamic load balancing and high error tolerance management technology. An easy-touse"tree”multi-level task distribution system is implemented. A fast, efficient and stable drug virtual screening task distribution, calculation and result analysis function is realized, and the computing efficiency is nearly linear. Then, heterogeneous computing technology is used to complete the drug virtual screening of more than 2 billion compounds, for two different active sites for COVID-19, on the domestic super computing system, which provides a powerful computing guarantee for the super large-scale rapid virtual screening of explosive malignant infectious diseases. © 2023, Journal of Computer Engineering and Applications Beijing Co., Ltd.;Science Press. All rights reserved.

Investigation of demographic implicit discrimination and disparate impact in chest radiography image-based AI for COVID-19 severity prediction

It is important to evaluate medical imaging artificial intelligence (AI) models for possible implicit discrimination (ability to distinguish between subgroups not related to the specific clinical task of the AI model) and disparate impact (difference in outcome rate between subgroups). We studied potential implicit discrimination and disparate impact of a published deep learning/AI model for the prediction of ICU admission for COVID-19 within 24 hours of imaging. The IRB-approved, HIPAA-compliant dataset contained 8,357 chest radiography exams from February 2020-January 2022 (12% ICU admission within 24 hours) and was separated by patient into training, validation, and test sets (64%, 16%, 20% split). The AI output was evaluated in two demographic categories: sex assigned at birth (subgroups male and female) and self-reported race (subgroups Black/African-American and White). We failed to show statistical evidence that the model could implicitly discriminate between members of subgroups categorized by race based on prediction scores (area under the receiver operating characteristic curve, AUC: median [95% confidence interval, CI]: 0.53 [0.48, 0.57]) but there was some marginal evidence of implicit discrimination between members of subgroups categorized by sex (AUC: 0.54 [0.51, 0.57]). No statistical evidence for disparate impact (DI) was observed between the race subgroups (i.e. the 95% CI of the ratio of the favorable outcome rate between two subgroups included one) for the example operating point of the maximized Youden index but some evidence of disparate impact to the male subgroup based on sex was observed. These results help develop evaluation of implicit discrimination and disparate impact of AI models in the context of decision thresholds © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.

Fast de novo antibody structure prediction with atomic accuracy

Background: In the field of antibody engineering, an essential task is to design a novel antibody whose paratopes bind to a specific antigen with correct epitopes. Understanding antibody structure and its paratope can facilitate a mechanistic understanding of its function. Therefore, antibody structure prediction from its sequence alone has always been a highly valuable problem for de novo antibody design. AlphaFold2 (AF2), a breakthrough in the field of structural biology, provides a solution to this protein structure prediction problem by learning a deep learning model. However, the computational efficiency and undesirable prediction accuracy on antibody, especially on the complementarity-determining regions limit its applications in de novo antibody design. Method(s): To learn informative representation of antibodies, we trained a deep antibody language model (ALM) on curated sequences from observed antibody space database via a well-designed transformer model. We also developed a novel model named xTrimoABFold++ to predict antibody structure from antibody sequence only based on the pretrained ALM as well as efficient evoformers and structural modules. The model was trained end-to-end on the antibody structures in PDB by minimizing the ensemble loss of domain-specific focal loss on CDR and the frame aligned point loss. Result(s): xTrimoABFold++ outperforms AF2 and OmegaFold, HelixFold-Single with 30+% improvement on RMSD. Also, it is 151 times faster than AF2 and predicts antibody structure in atomic accuracy within 20 seconds. In recently released antibodies, for example, cemiplimab of PD1 (PDB: 7WVM) and cross-neutralizing antibody 6D6 of SARS-CoV-2 (PDB: 7EAN), the RMSD of xTrimoABFold++ are 0.344 and 0.389 respectively. Conclusion(s): To the best of our knowledge, xTrimoABFold++ achieved the state-of-the-art in antibody structure prediction. Its improvement on both accuracy and efficiency makes it a valuable tool for de novo antibody design, and could make further improvement in immuno-theory.

The role of dorsolateral prefrontal cortex on placebo effect of regulating social pain: A TMS study

Under the influence of the novel coronavirus epidemic, some negative social events, such as separation of family or friends and home isolation have increased. These events can cause negative emotion experiences similar to physical pain, thus they are called social pain. Placebo effect refers to the positive response to the inert treatment with no specific therapeutic properties, which has been shown to be one of the effective ways to alleviate social pain. Studies have shown that the dorsolateral prefrontal cortex (DLPFC) plays a key role in placebo effect. Therefore, this study aimed to explore whether activating DLPFC by using transcranial magnetic stimulation (TMS) could improve the ability of placebo effects to regulate social pain. Besides, we also combined neuroimaging and neuromodulation techniques to provide bidirectional evidence for the role of the DLPFC on placebo effects. We recruited a total of 100 participants to finish the task of negative emotional rating of the social exclusion images. Among them, 50 participants were stimulated by TMS at the right DLPFC (rDLPFC), while the others were assigned to the sham group. This study contained two independent variables. The between-subject variable was TMS group (rDLPFC-activated group or sham group) and the within-subject variable was placebo type (no-placebo and placebo). All participants received nasal spray in two blocks. In the no-placebo condition, participants were instructed that they would receive a saline nasal spray which helped to improve physiological readings;in placebo block, participants were told to administrate an intranasal fluoxetine spray (saline nasal spray in fact) that could reduce unpleasantness within 10 minutes. To strengthen the expectation of intranasal fluoxetine, participants viewed a professional introduction to fluoxetine's clinical and academic usage including downregulating negative emotion, such as fear, anxiety, and disgust. Participants who received the placebo block first would be reminded that fluoxetine's effect was over before the next block to reduce the carry-over for the following block. Self-reported negative emotional and electroencephalogram data were recorded. There was a significant two-way interaction of TMS group and placebo type. Results showed that compared with the sham group, participants in the rDLPFC-activated group reported less negative emotional feeling and had a lower amplitude of the late positive potential (LPP) in placebo condition, a component that reflects the emotional intensity, suggesting that activating rDLPFC can improve the ability of placebo effect to regulate social pain. The above finding suggested that activating DLPFC can improve the placebo effect of regulating negative emotion. Moreover, this study is the first attempt to investigate the enhancement of placebo effects by using TMS on emotion regulation. The findings not only support the critical role of DLPFC on placebo effect using neuroimaging and neuromodulation techniques, but also provide a potential brain target for treating emotional regulation deficits in patients with psychiatric disorders. © 2023 WANG Mei.

Numerical Simulation of the COVID-19 Herd Immunity Based on Complex Network Modeling

Constructing an epidemic dynamic model and exploring the spreading law of epidemic have very important theoretical significance for epidemic prevention and control. Based on the existing homogeneous mixing model, in view of the increasingly obvious heterogeneity of individual contact relationships, and each individual is in a different contact relationship, a dynamic small-world network model that takes into account individual status. Contact tracking has been established to simulate the spread of the COVID-19 in society. By comparing the simulation results, the rationality of the built model is explained. On this basis, the simulation calculated the impact of the network topology and the proportion of vaccinated people on the spread of the COVID-19, analyzed the critical value of herd immunity. The established propagation model is reasonable, and feasible to achieve herd immunization by vaccination. © 2023 Editorial Borad of Complex Systems and Complexity Science. All rights reserved.

Visual Analysis of Social Robots in Twitter on China Agenda Setting

With the development and progress of intelligent algorithms, more and more social robots are used to interfere with the information transmission and direction of international public opinion. This paper takes the agenda of COVID-19 in Twitter as the breakthrough point, and through the methods of web crawler, Twitter robot detection, data processing and analysis, aims at the agenda setting of social robots for China issues, that is, to carry out data visualization analysis for the stigmatized China image. Through case analysis, concrete and operable countermeasures for building the international communication system of China image were provided. © 2022 IEEE.

Contact Tracing over Uncertain Indoor Positioning Data

Pandemics often cause dramatic losses of human lives and impact our societies in many aspects such as public health, tourism, and economy. To contain the spread of an epidemic like COVID-19, efficient and effective contact tracing is important, especially in indoor venues where the risk of infection is higher. In this work, we formulate and study a novel query called Indoor Contact Query (<sc>ICQ</sc>) over raw, uncertain indoor positioning data that digitalizes people's movements indoors. Given a query object <inline-formula><tex-math notation="LaTeX">$o$</tex-math></inline-formula>, e.g., a person confirmed to be a virus carrier, an <sc>ICQ</sc> analyzes uncertain indoor positioning data to find objects that most likely had close contact with <inline-formula><tex-math notation="LaTeX">$o$</tex-math></inline-formula> for a long period of time. To process <sc>ICQ</sc>, we propose a set of techniques. First, we design an enhanced indoor graph model to organize different types of data necessary for <sc>ICQ</sc>. Second, for indoor moving objects, we devise methods to determine uncertain regions and to derive positioning samples missing in the raw data. Third, we propose a query processing framework with a close contact determination method, a search algorithm, and the acceleration strategies. We conduct extensive experiments on synthetic and real datasets to evaluate our proposals. The results demonstrate the efficiency and effectiveness of our proposals. IEEE

Classic Augmentation based Classifier Generative Adversarial Network (CACGAN) for COVID-19 Diagnosis

Computer-aided diagnosis of COVID-19 from lung medical images has received increasing attention in previous clinical practice and research. However, developing such automatic model is usually challenging due to the requirement of a large amount of data and sufficient computer power. With only 317 training images, this paper presents a Classic Augmentation based Classifier Generative Adversarial Network (CACGAN) for data synthetising. In order to take into account, the feature extraction ability and lightness of the model for lung CT images, the CACGAN network is mainly constructed by convolution blocks. During the training process, each iteration will update the discriminator's network parameters twice and the generator's network parameters once. For the evaluation of CACGAN. This paper organized multiple comparison between each pair from CACGAN synthetic data, classic augmented data, and original data. In this paper, 7 classifiers are built, ranging from simple to complex, and are trained for the three sets of data respectively. To control the variable, the three sets of data use the exact same classifier structure and the exact same validation dataset. The result shows the CACGAN successfully learned how to synthesize new lung CT images with specific labels. © 2023 SPIE.

Where can I travel to? The difference in support for COVID-19 travel restrictions between Chinese Xiamen islanders and mainlanders

Previous research has shown that there are vast cross-cultural differences in attitudes toward COVID-19 travel restrictions. Yet, pinpointing the specific role of any single factor in explaining cross-cultural variability is difficult when comparing cultural communities that differ along myriad dimensions. Taking a 'just minimal difference' approach that removes the effects of extraneous variables, the present research focuses on how islandness can account for variability in travel intentions during the pandemic. Combining retrospective self-report assessment with a dynamic behavioural choice regarding travel intention during COVID-19, the present research examined travel attitudes and behaviours in Chinese Xiamen islanders and mainlanders that share the same geographic environment, language, ethnicity, and socioeconomic status, but vary in their implicit individualism. Results across two studies revealed that Chinese Xiamen islanders were less supportive of travel and mobility restrictions than mainlanders who all lived near the coast. Additionally, it was found that implicit individualism mediated the link between islandness and travel attitudes. Together, this paper not only presents the first empirical evidence for the role of geographic environment in the emergence of attitudes toward restrictive travel limitations, but potentially informs tourism management and revival in the era of COVID-19.

Effect of Azovudine on Hepatic and Renal Function in Patients with COVID-19：a Case Series Study

Background Azovudine is a widely used antiviral drug for COVID-19 in China，but published trials on its effect on hepaticand renal function are extremely scarce. Objective To explore the changes of in hepatic and renal function in patients with COVID-19 infection after using Azovudine，so as to provide a reference for thesafe use of Azovudine in patients with renal insufficiency. Methods Inpatients ina tertiary general hospitalwho used Azovudine for COVID-19 from December 26，2022 to December 31，2022 were consecutively included in the retrospective study and divided into the normal group，mild injury group，moderate injury group，severe injury group，and end-stage groupaccording to estimated glomerularrate（eGFR）levels. The changes of biochemical parametersof liver and kidney including alanine aminotransferase（ALT），aspartate aminotransferase（AST），alkaline phosphatase （ALP），albumin（ALB），total bilirubin（TB），serum creatinine （Scr），eGFR were observed in each group；the formula D_FR=D_NL×［1-F_k （1-K_f）］ was used to correct the maintenance dose of Azivudine in patients with eGFR<60 mL·min-1·（1.73 m2）-1. The patients were divided into the corrected group and uncorrected group according to whether they were administered according to this formula，the biochemical parameters of liver and kidney were compared between the two groups. Results Among 322 patients who used Azovudine，190 patients met the inclusion and exclusion criteria. After grouping by the level of eGFR，there were statistically significant differences in the distribution of age，COVID-19 severity，peak procalcitonin（PCT）values，antihypertensive drugs，loop diuretics and Azovudine maintenance dose in each group（P<0.05）；there were 73 cases（38.4%） with elevated ALT level after Azovudine treatment，and 68 cases（93.2%） with elevated ALT level within one time of the upper normal limit；eGFR decreased in 58 cases（30.5%），of which 7 cases（12.1%） dropped to the next renal function grade；regardless of the grade of renal injury，there were no deterioration in eGFR，ALT，AST，TB，ALP and albumin after the use of conventional dose or corrected dose of Azivudine（P>0.05）；because the patients with moderate and severe renal injury were dose-corrected with Azivudine，the safety of this population was not compared if the dose was not corrected. Conclusion The use of Azivudine is prone to cause the elevation of ALT level and the decrease of eGFR，but the injury with clinical significance is 2.6% and 3.7%，respectively；there was no aggravation of liver and kidney injury in patients with moderate and severe kidney injury after using the corrected dose of Azivudine，however，this conclusion needs to be confirmed in a multicenter randomized controlled study with a large sample. © 2023 Chinese General Practice. All rights reserved.

Assessing an AI-based Smart Imagery Framing and Truthing (SIFT) system to assist radiologists annotating lung abnormalities on chest X-ray images for development of deep learning models

To assess a Smart Imagery Framing and Truthing (SIFT) system in automatically labeling and annotating chest X-ray (CXR) images with multiple diseases as an assist to radiologists on multi-disease CXRs. SIFT system was developed by integrating a convolutional neural network based-augmented MaskR-CNN and a multi-layer perceptron neural network. It is trained with images containing 307,415 ROIs representing 69 different abnormalities and 67,071 normal CXRs. SIFT automatically labels ROIs with a specific type of abnormality, annotates fine-grained boundary, gives confidence score, and recommends other possible types of abnormality. An independent set of 178 CXRs containing 272 ROIs depicting five different abnormalities including pulmonary tuberculosis, pulmonary nodule, pneumonia, COVID-19, and fibrogenesis was used to evaluate radiologists' performance based on three radiologists in a double-blinded study. The radiologist first manually annotated each ROI without SIFT. Two weeks later, the radiologist annotated the same ROIs with SIFT aid to generate final results. Evaluation of consistency, efficiency and accuracy for radiologists with and without SIFT was conducted. After using SIFT, radiologists accept 93% SIFT annotated area, and variation across annotated area reduce by 28.23%. Inter-observer variation improves by 25.27% on averaged IOU. The consensus true positive rate increases by 5.00% (p=0.16), and false positive rate decreases by 27.70% (p<0.001). The radiologist's time to annotate these cases decreases by 42.30%. Performance in labelling abnormalities statistically remains the same. Independent observer study showed that SIFT is a promising step toward improving the consistency and efficiency of annotation, which is important for improving clinical X-ray diagnostic and monitoring efficiency. © 2023 SPIE.

Epidemiological Survey of the Prevalence and Associated Factors of Mental Disorders in Xinjiang Uygur Autonomous Region

Background Socioeconomic development,lifestyle changes and the COVID-19 pandemic all have an impact on people's mental and physical health,which may affect the prevalence of mental disorders. Currently,there is still no sufficient epidemiological information of mental disorders in Xinjiang. Objective To investigate the prevalence and influencing factors of common mental disorders among people aged 15 and above in northern Xinjiang,then compare the data with those of their counterparts in southern Xinjiang,and summarize the overall prevalence of common mental disorders in Xinjiang,providing a scientific basis for the formulation of corresponding mental health plans. Methods From November 2021 to July 2022,a multistage,stratified,random sampling method was used to select 3 853 residents from northern Xinjiang to attend a survey. General Demographic Questionnaire,and self-assessment scales(the 12-Item General Health Questionnaire,Mood Disorder Questionnaire,Symptom Checklist-90,etc.) and other assessment scales(Hamilton Depression Inventory,Bech-Rafaelsen Mania Rating Scale,Brief Psychiatric Rating Scale,etc.) were used as survey instruments. Mental disorders were diagnosed by the ICD-10 classification of mental and behavioral disorders by two psychiatrists with at least five years' working experience, or by a chief or associate chief psychiatrist when there is an inconsistency between the diagnoses made by the two psychiatrists. Results The point prevalence rate and age-adjusted rate of common mental disorders in northern Xinjiang were 9.71% (374/3 853) and 10.07%,respectively. The point prevalence rate and age-adjusted rate of common mental disorders in the whole Xinjiang were 9.69%(750/7 736)and 9.90%,respectively. The point prevalence rates of mood disorders,anxiety disorders,schizophrenia,organic mental disorders,and mental retardation in northern Xinjiang were 4.83%(374/7 736),3.63% (281/7 736),0.63%(49/7 736),0.23%(18/7 736),and 0.36%(28/7 736),respectively. Multivariate Logistic regression analysis for northern Xinjiang showed that:the risk of mood disorders in females was 1.854 times higher than that in males 〔95%CI(1.325,2.593)〕;The risk of mood disorders increased by 5.210 times in 25-34-year-olds 〔95%CI(1.348, 20.143)〕 and 3.863 times in 35-44-year-olds 〔95%CI(1.030,14.485)〕 compared with that in those aged ≥ 65 years;The risk of mood disorders increased by 0.199 times in those with high school or technical secondary school education 〔95%CI (0.078,0.509)〕 and 0.147 times in those with two- or three-year college and above education 〔95%CI(0.056,0.388)〕 compared with that in illiteracies. The risk of anxiety disorder in females was 1.627 times higher than that in males 〔95%CI (1.144, 2.315)〕;The risk of anxiety disorder increased by 0.257 times in 15-24-year-olds 〔95%CI(0.091,0.729)〕,0.243 times in 45-54-year-olds 〔95%CI(0.101,0.583)〕,and 0.210 times in 55-64-year-olds 〔95%CI(0.067,0.661)〕 compared to that of those aged ≥ 65 years old. The risk of schizophrenia among people living in villages or towns was 4.762 times higher than that of those living in cities 〔95%CI(1.705,13.300)〕;The risk of schizophrenia among people with high school or technical secondary school education was 0.079 times higher than that of illiteracies 〔95%CI(0.015,0.405)〕. Conclusion The prevalence of mood disorders and anxiety disorders is high among all types of mental disorders in Xinjiang. Females,rural people,or low educated people in northern Xinjiang are more prone to various types of mental disorders. © 2023 Chinese General Practice. All rights reserved.

Longitudinal robustness of a thoracic radiographic AI model for COVID-19 severity prediction

The 'ging' of artificial intelligence/machine learning (AI/ML) models after initial development and evaluation is known to frequently occur and can pose substantial problems. When there are changes in population, disease characteristics, imaging equipment, or protocols, model performance may start to deteriorate, and the performance predicted in a research setting may no longer hold after deployment (either in a clinical setting or in further research). This data shift phenomenon is a common problem in AI/ML. We trained and evaluated a previously in-house developed AI/ML model for COVID severity prediction using two COVID-19-positive consecutive adult patient cohorts from a single institution. The first cohort was from the time that the Delta strain was dominant accounting for <95% of cases (June 24-December 11, 2021, 820 patients, 1331 chest radiographs (CXRs)) and the second cohort was from the time that the Omicron variant was dominant (Jan 1-21, 2022, 656 patients, 970 CXRs). Inclusion criteria were COVID-positivity and the availability of CXR imaging exams, in general for patients not admitted to ICU and prior to ICU admission for those patients admitted to ICU as part of their treatment. Exclusion criteria were image acquisition in ICU or the presence of mechanical ventilation. Our image-based AI/ML model was trained to predict, based on each frontal CXR from a COVID-positive patient, whether this patient would be admitted to ICU within a 24, 48, 72, or 96-hour window. The model was evaluated 1) in a cross-sectional test when trained on a subset/tested on an independent subset of the Delta cohort, 2) similarly for the Omicron cohort, and 3) in a longitudinal test when trained on the Delta cohort/tested on the Omicron cohort. Cohorts were similar in ICU admission rate and fraction of portable CXRs, while immunization rate was higher for the Omicron cohort. The model did not demonstrate signs of aging with performances in the longitudinal test being very similar to those within the Delta cohort, e.g., an area under the ROC curve in the task of predicting ICU admission within 24 hours of 0.76 [0.68;0.84] when trained/tested within the Delta cohort and 0.77 [0.73;0.80] for the longitudinal test (p>0.05). The performance within the Omicron cohort was similar as well, at 0.76 [0.66;0.84]. Our AI/ML model for COVID-severity prediction did not demonstrate signs of aging in a longitudinal test when trained on the Delta cohort and applied as-is to the Omicron cohort. © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.

Association of interleukin-6 and CD4+ T cells and two-week prognosis of patients with COVID-19: a predictive role.

OBJECTIVE:  The aim of this study was to determine the association of inflammation and immune responses with the outcomes of patients at various stages, and to develop risk stratification for improving clinical practice and reducing mortality. PATIENTS AND METHODS: We included 77 patients with primary outcomes of either death or survival. Demographics, clinical features, comorbidities, and laboratory tests were compared. Linear, logistic, and Cox regression analyses were performed to determine prognostic factors. RESULTS: The average age was 59 years (35-87 years). There were 12 moderate cases (16.2%), 42 severe cases (54.5%), and 23 critical cases (29.9%); and 41 were male (53.2%). Until March 20, 68 cases were discharged (88.3%), and nine critically ill males (11.7%) died. Interleukin-6 (IL-6) levels on the 1st day were compared with IL-6 values on the 14th day in the severe and the critically ill surviving patients (F=4.90, p=0.034, ß=0.35, 95% CI: 0.00-0.10), and predicted death in the critically ill patients (p=0.028, ß=0.05, OR: 1.05, 95% CI: 1.01-1.10). CD4+ T-cell counts at admission decreased the hazard ratio of death (p=0.039, ß=-0.01, hazard ratio=0.99, 95% CI: 0.98-1.00, and median survival time 13.5 days). CONCLUSIONS: The present study demonstrated that IL-6 levels and CD4+ T-cell count at admission played key roles of predictors in the prognosis, especially for critically ill patients. High levels of IL-6 and impaired CD4+t cells are seen in severe and critically ill patients with COVID-19.

Traffic Flow Forecasting in the COVID-19: A Deep Spatial-temporal Model Based on DiscreteWavelet Transformation

Traffic flowprediction has always been the focus of research in the field of Intelligent Transportation Systems, which is conducive to the more reasonable allocation of basic transportation resources and formulation of transportation policies. The spread of COVID-19 has seriously affected the normal order in the transportation sector. With the increase in the number of infected people and the government's anti-epidemic policy, human outgoing activities have gradually decreased, resulting in increasingly obvious discreteness and irregularities in traffic flow data. This article proposes a deep-space time traffic flow prediction model based on discrete wavelet transform (DSTM-DWT) to overcome the highly discrete and irregular nature of the new crown epidemic. First, DSTM-DWT decomposes traffic flow into discrete attributes, such as flow trend, discrete amplitude, and discrete baseline. Second, we design the spatial relationship of the transportation network as a graph and integrate the new crown pneumonia epidemic data into the characteristics of each transportation node. Then, we use the graph convolutional network to calculate the spatial correlation of each node, and the temporal convolutional network to calculate the temporal correlation of the data. In order to solve the problem of high discreteness of traffic flow data during the epidemic, this article proposes a graph memory network (GMN), which is used to convert discrete magnitudes separated by discrete wavelet transform into highdimensional discrete features. Finally, use DWT to segment the predicted traffic data, and then perform the inverse discrete wavelet transform between the newly segmented traffic trend and discrete baseline and the discrete model predicted by GMN to obtain the final traffic flow prediction result. In simulation experiments, this work was compared with the existing advanced baselines to verify the superiority of DSTM-DWT.

University faculty's informal learning and professional reflections: text mining for processing interviews

Purpose: As university faculty faced new challenges, such as rapid digital social and the coronavirus disease 2019 (COVID-19) response, this study aimed to identify the daily changes in the interaction between the faculty and the organizational environment (colleague, policy and new issue) by exploring their recent dynamic educational efforts and the professional development. Design/methodology/approach: This is a study wherein perceptions of 20 faculty from 15 universities and colleges were collected through in-depth online interviews. The authors analyzed interview data by arranging and visualizing the analyzed data using network clustering. Further, they applied the Latent Dirichlet allocation of the topic modeling to monitor the appropriate number of clusters, ultimately determined as four clusters using partial clustering. Findings: The results showed that university faculty spontaneously tried to solve the problems through informal learning while the commitment to peer learning was deepening, reflecting the collectivist orientation nature of Chinese culture. Besides, the faculty also required support to reflect on their daily efforts for professional development. These results about their various learning routines prove the justification for the faculty's professional development to be discussed from the "learning by doing” perspective of lifelong learning. Originality/value: This study proved the significance of informal learning for university faculty's professional development and the reasonable value of peer learning, and provided insights into how the Chinese context may influence university faculty's informal learning experience. © 2023, Emerald Publishing Limited.

UNESCO practices under the SDG4 and COVID-19 response framework: Topic modeling from 2003 to 2021

This study focused on the impacts of COVID-19 on SDG4 to resolve inequality through education and explored UNESCO's educational practices. We used text mining to analyze strategic and crisis-related reports published by UNESCO from 2003 to 2021 and LDA topic modeling analysis was used to determine their latent contexts. Two topics related to education strategies were 'sustainable development' and 'system and organization'. According to the themes, non-formal, formal and informal learning and skills and TVET topics were derived for lifelong learning, school and teacher, emergency and peace, policy and framework in the theme of crisis and conflict. Finally, latent topics during each MDGs, SDGs and COVID-19 period showed insignificant changes. However, compared to before the 2014 MDGs, strategic discourses tended to be discussed in detail. Moreover, we noted the change in global discourse from globalization to digital innovation. After the pandemic, the international community has emphasized the role of teachers and improved internet access for interaction. Such recommendations were intended to bridge the gap between countries including developing countries. As an alternative, UNESCO has suggested various partnership practices but there are nevertheless limitations that cannot be solved through a partnership or educational support. Therefore, reaching SDG4 requires global efforts to change the world by coordinating specific target countries and various social factors surrounding the countries' interior and exterior. © 2023 by the authors.

COVID-19 pandemic and hotel property performance

Purpose: The purpose of this study is to test the local impact of COVID-19 pandemic on hotel performance at the individual property level, and further examine the roles of hotel attributes and business mix in potentially moderating or intensifying the impact of a crisis. Design/methodology/approach: Using a sample of 5,090 hotel properties in Texas, USA from January 2020 to December 2021, this study estimates a monthly hotel performance model to evaluate how the pandemic affected hotels' operational performance based on revenue per available room. Findings: Results show that a 10% increase in the monthly number of confirmed COVID-19 cases led to a 0.522% decrease in hotel performance. Also, a series of moderators were identified within the pandemic–performance relationship: the negative impact of the pandemic was more severe among higher-end hotels and newer hotels;urbanization and localization diseconomies prevailed during the pandemic;and there was a smaller negative effect of COVID-19 on high rated hotels in the category of economy hotels. Originality/value: The moderators highlighted in this paper shed light on the heterogeneity of COVID-19's effects on hotel operations. Findings enrich the hospitality literature by considering business resilience in relation to the pandemic. © 2023, Emerald Publishing Limited.

Integrated surveillance and early warning system for emerging infectious diseases based on One Health concept: Structures and innovations.

One Health is an upgrade and optimization of health concepts, which recognizes the integrated health of the human-animal-environment. It emphasizes the use of interdisciplinary collaboration, multi-sectoral coordination, and multi-organizational One Health approaches to solve scientific questions. The surveillance and early warning system is the basis of public health emergency prevention and control. The COVID-19 pandemic and the emerging infectious disease (EID) have put great challenges on the existing surveillance and early warning systems worldwide. Guided by the concept of One Health, we attempt to build a new pattern of integrated surveillance and early warning system for EID. We will detail the system including the One Health-based organizational structure, zoonotic and environmental science surveillance network, EID reporting process, and support and guarantee from education and policy. The integrated surveillance and early warning system for EID constructed here has practical and application prospects, and will provide guidance for the prevention and control of COVID-19 and the possible EID in the future.Copyright © 2022, National Institute of Parasitic Diseases. All rights reserved.

Speech Recognition Using Intelligent Piezoresistive Sensor Based on Polystyrene Sphere Microstructures

Rapid advances in wearable sensing technology have demonstrated unprecedented opportunities for artificial intelligence. In comparison with the traditional hand-held electrolarynx, a wearable and intelligent artificial throat with sound-sensing ability is a more comfortable and versatile method to assist disabled people with communication. Herein, a piezoresistive sensor with a novel configuration is demonstrated, which consists of polystyrene (PS) spheres as microstructures sandwiched between silver nanowires and reduced graphene oxide layers. In fact, changes in the device's conducting patterns are obtained by spay-coating the various weight ratios and sizes of the PS microspheres, which is a fast and convenient way to establish microstructures for improving sensitivity. The wearable artificial throat device also exhibits high sensitivity, fast response time, and ultralow intensity level detection. Moreover, the device's excellent mechanical-electrical performance allows it to detect subtle throat vibrations that can be converted into controllable sounds. In this case, an intelligent artificial throat is achieved by combining a deep learning algorithm with a highly flexible piezoresistive sensor to successfully recognize five different words (help, sick, patient, doctor, and COVID) with an accuracy exceeding 96%. Herein, new opportunities in voice control as well as other human-machine interface applications are opened.