Learning Social Meta-knowledge for Nowcasting Human Mobility in Disaster

Human mobility nowcasting is a fundamental research problem for intelligent transportation planning, disaster responses and management, etc. In particular, human mobility under big disasters such as hurricanes and pandemics deviates from its daily routine to a large extent, which makes the task more challenging. Existing works mainly focus on traffic or crowd flow prediction in normal situations. To tackle this problem, in this study, disaster-related Twitter data is incorporated as a covariate to understand the public awareness and attention about the disaster events and thus perceive their impacts on the human mobility. Accordingly, we propose a Meta-knowledge-Memorizable Spatio-Temporal Network (MemeSTN), which leverages memory network and meta-learning to fuse social media and human mobility data. Extensive experiments over three real-world disasters including Japan 2019 typhoon season, Japan 2020 COVID-19 pandemic, and US 2019 hurricane season were conducted to illustrate the effectiveness of our proposed solution. Compared to the state-of-the-art spatio-temporal deep models and multivariate-time-series deep models, our model can achieve superior performance for nowcasting human mobility in disaster situations at both country level and state level. © 2023 ACM.

Organic Electrochemical Transistors functionalized with Protein Minibinders for Sensitive and Specific Detection of SARS-CoV-2

There is a need for rapid, sensitive, specific, and low-cost virus sensors. Recent work has demonstrated that organic electrochemical transistors (OECTs) can detect the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein. Here, a simple and low-cost approach to the fabrication of OECT devices with excellent stability and unprecedented sensitivity and specificity for the detection of SARS-CoV-2 virus is demonstrated. The devices rely on the engineered protein minibinder LCB1, which binds strongly to SARS-CoV-2. The resulting devices exhibit excellent sensitivity for the detection of SARS-CoV-2 virus and SARS-CoV-2 spike protein receptor binding domain (RBD). These results demonstrate a simple, effective, and low-cost biomolecular sensor applicable to the real-time detection of SARS-CoV-2 virus and a general strategy for OECT device design that can be applied for the detection of other pathogenic viruses.

Online 8-Form Tai Chi Chuan Training and Evaluation System Based on Pose Estimation

Exercise at home has already been a common behavior in the current world, especially in the post-COVID-19 era, even some athletes need to do physical fitness at home to keep their state due to the quarantine. So, the importance of online physical training and evaluation is highly increasing. In this work, we build an online 8-form Tai Chi Chuan (TCC) training and evaluation system, which provides a platform for coaches and users to conduct TCC training and evaluation online. Coaches formulate an evaluation rule and upload coaching videos to the platform, then users watch videos online and submit their own recordings, finally, users will get a score of their recordings. To complete this task, we propose a video capture method to record users' sports exercise videos from different perspectives, construct a 3D pose estimation model to identify human pose from captured video, and propose an evaluation model which can judge users' performance and assign a score to each video. To test our proposed models, we make a dataset consisting of key pose frames of TCC, and the key pose frames are extracted from users' TCC exercise videos. We use the dataset to train our models and assign scores to key poses, then compare the results with scores given by professional TCC players. In addition, we add all key pose scores from every single user together and obtain the whole score of an exercise video. The experiment results show that the error between scores assigned by our models and scores given by professional players does not exceed 1.6 in most scoring of a whole exercise video, and Root Mean Square Error (RMSE) is about 0.75 in the scoring of each key pose. © 2022 IEEE.

Reactive Air Disinfection Technologies: Principles and Applications in Bioaerosol Removal

As COVID-19 and other infectious diseases continue to spread globally, removing airborne pathogens from confined spaces such as buildings, transportation carriers, and stations is becoming increasingly crucial to curbing transmission and reducing human infection rates. Bioaerosols can act as vectors or media that could store and transport air pollutants and pathogens. To mitigate the adverse effects of bioaerosols and effectively control epidemics, this work reviews the current state-of-the-art air purification processes and technologies available on the market or demonstrated in laboratory and industrial settings, including ozone oxidation, UV disinfection, and photocatalysis. These reactive air purification processes can be used in conjunction with adsorption or filtration-based systems to enhance disinfection besides the physical capture of particulates or the removal of volatile organic compounds (VOCs). This review aims to provide a concise yet comprehensive overview of various reactive air purification technologies. Their principles, applications, and limitations are briefly discussed to provide insight and guidelines for further development of new air purification processes to address emerging airborne contaminant issues. © 2023 American Chemical Society.

A COVID-19 Patient Discharged According to Strict Discharge Standards: Viral Negativity in Both Nasopharynx and Feces

Severe acute respiratory syndrome Coronavirus 2 (SARS-CoV-2) currently has spread all over the world. However, the dynamic characteristics of SARS-CoV-2 infections have not previously been described in detail. Here, we report a cured patient in West China Hospital, and describe the dynamic detection of SARS-CoV-2-RNA in different specimens and viral specific IgM and IgG antibodies in blood. The findings suggest that the fecal SARS-CoV-2-RNA negativity may be considered as a new standard for de isolation. Serum IgM and IgG antibodies detection were helpful for early diagnosis of SARS-CoV-2 infection and judgment of patients in recovery stage, respectively. © 2022 Journal of Bone and Joint Surgery Inc.. All rights reserved.

A Survey on Data-driven COVID-19 and Future Pandemic Management

The COVID-19 pandemic has resulted in more than 440 million confirmed cases globally and almost 6 million reported deaths as of March 2022. Consequently, the world experienced grave repercussions to citizens' lives, health, wellness, and the economy. In responding to such a disastrous global event, countermeasures are often implemented to slow down and limit the virus's rapid spread. Meanwhile, disaster recovery, mitigation, and preparation measures have been taken to manage the impacts and losses of the ongoing and future pandemics. Data-driven techniques have been successfully applied to many domains and critical applications in recent years. Due to the highly interdisciplinary nature of pandemic management, researchers have proposed and developed data-driven techniques across various domains. However, a systematic and comprehensive survey of data-driven techniques for pandemic management is still missing. In this article, we review existing data analysis and visualization techniques and their applications for COVID-19 and future pandemic management with respect to four phases (namely, Response, Recovery, Mitigation, and Preparation) in disaster management. Data sources utilized in these studies and specific data acquisition and integration techniques for COVID-19 are also summarized. Furthermore, open issues and future directions for data-driven pandemic management are discussed.

Forecasting Trend of Coronavirus Disease 2019 using Multi-Task Weighted TSK Fuzzy System

Artificial intelligence-(AI) based fog/edge computing has become a promising paradigm for infectious disease. Various AI algorithms are embedded in cooperative fog/edge devices to construct medical Internet of Things environments, infectious disease forecast systems, smart health, and so on. However, these systems are usually done in isolation, which is called single-task learning. They do not consider the correlation and relationship between multiple/different tasks, so some common information in the model parameters or data characteristics is lost. In this study, each data center in fog/edge computing is considered as a task in the multi-task learning framework. In such a learning framework, a multi-task weighted Takagi-Sugeno-Kang (TSK) fuzzy system, called MW-TSKFS, is developed to forecast the trend of Coronavirus disease 2019 (COVID-19). MW-TSKFS provides a multi-task learning strategy for both antecedent and consequent parameters of fuzzy rules. First, a multi-task weighted fuzzy c-means clustering algorithm is developed for antecedent parameter learning, which extracts the public information among all tasks and the private information of each task. By sharing the public cluster centroid and public membership matrix, the differences of commonality and individuality can be further exploited. For consequent parameter learning of MW-TSKFS, a multi-task collaborative learning mechanism is developed based on ϵ-insensitive criterion and L2 norm penalty term, which can enhance the generalization and forecasting ability of the proposed fuzzy system. The experimental results on the real COVID-19 time series show that the forecasting tend model based on multi-task the weighted TSK fuzzy system has a high application value. © 2021 Association for Computing Machinery.

Detection of SARS-CoV-2 Using a Miniaturized Spectrometer Chip: A Comparative Study Against Benchtop Spectrometer and Its Potential Application to Handheld Detection

A global pandemic of SARS-CoV-2 was caused around the world. The virus is highly contagious and rapidly spreads. Early detection of the virus is crucial to prevent its spread and control outbreaks. Owing to the drawbacks of waiting time and high cost involved in polymerase chain reaction (PCR) testing, low-cost and accurate detection setups with the possibility of being realized as portable systems are desirable. In this study, we examined the feasibility of using a small spectrometer in conjunction with optical biosensors as a measurement system. According to the experimental results related to different concentrations of SARS-CoV-2 ranging from 106 to 102 copies/mL, the surface-mounted device (SMD) size spectrometer and benchtop fiber-optic spectrometer showed good agreement, demonstrating the possibility of using tiny spectrometers to detect the virus at different concentrations using optical biosensors. © 2022 ACM.

Patient-reported reasons for no-shows to screening mammogram appointments among African American women

Background: Mammography screening significantly reduces breast-cancer related mortality;however, many women fail to undergo screening as recommended by national guidelines. No-shows are responsible for a significant proportion of delayed or missed cancer screening exams. Further, no-shows disproportionately affect underserved and minority populations. We previously identified a high no-show rate for screening mammograms among patients seeking care our institution. African American (AA) women were almost three times more likely to no-show than non-Hispanic white women. The racial disparity in no-shows persisted after adjustment for socioeconomic factors. The objective of this survey study was to identify reasons for missed mammogram screening appointments among AA women. Methods: We conducted a survey (via mail or telephone) of AA women who missed their screening mammogram appointment in summer 2021. Using a structured survey instrument, we collected information on patient-specific and health service barriers. Patient-specific barriers included procedure-related concerns (e.g., concern about discomfort), cognitive-emotional factors (e.g., fear of finding cancer), and changes in health status. Health service barriers included logistical factors (e.g., transportation), cost (e.g., lack of insurance) and scheduling problems (e.g., forgot about appointment or scheduled at an inconvenient time). Here we describe the most common reasons for missed appointments and compared women who reported patient-specific versus health service barriers. Results: 255 women who no-showed for their appointment were contacted and 91 participated in the study survey (35.6% response rate). Most respondents (90%) attributed their no-show to at least one of the listed barriers. Nineteen (7.5%) attributed their no-show to COVID-19, but only 1 person reported this as their only barrier. Scheduling issues were the most commonly reported barriers (57.8%), followed by transportation (38.9%). Three-quarters of respondents reported health service barriers, while only 40.7% reported patient-related barriers. The most common patient-related barriers were cognitiveemotional (25%), changes in health status (20.9%) and procedure-related concerns (15.6%). The majority of respondents (82.6%) were interested in rescheduling their mammogram. Conclusions: Most appointment no-shows among surveyed AA women resulted from potentially preventable scheduling and transportation issues. Relatively few respondents reported cognitive-emotional or procedure-related concerns. Further, the majority of respondents were interested in rescheduling their mammogram;which suggests that these women remain motivated to undergo breast cancer screening. Programs which address preventable health-service related issues may help these women keep their appointments.

A Remotely Controlled Oropharyngeal Swab Sampling Robot and its Application in COVID-19 Prevention

Oropharyngeal swab sampling is the major viral nucleic acid detection method to diagnose COVID-19. Medical staff exposes themselves to the respiratory secretions of patients, which makes them vulnerable to infection. To protect medical staff, we summarize the clinical requirements for robot into five considerations (standardization, ergonomics, safety, isolation, and task allocation) and developed a remotely operated oropharyngeal swab sampling robot. With robot assistance, spatial isolation between medical staff and the patients can be achieved. We designed a hybrid force/position control scheme for the sampling robot to achieve intuitive operation and stable contact force. The experiment results on phantom tissue show that the sampling robot can achieve intuitive operation and stable contact on the soft posterior pharyngeal. Clinical trials for 20 volunteers and 2 patients diagnosed with COVID-19 are carried out. The results of the clinical trial indicated that the sampling robot can collect samples stably and effectively, and the contact force is gentler and more uniform. For two patients diagnosed with COVID-19, the robot sampling results are consistent with manual sampling. IEEE

Reliability and Resource Allocation and Recovery of Urban Transportation System Considering the Virus Transmission

The urban transport system is an integral part of a city and is essential for the proper functioning of other urban functional systems. To improve the resilience of urban transport systems under the background of the spreading COVID-19 epidemic, this paper predicts the number of patients of various types at each stage of epidemic development based on an improved infectious disease model for Wuhan and verifies the validity of the model using statistical methods. Then, a system reliability model is developed from the perspective of controlling the spread of the virus and reducing economic losses, and the optimal time points for urban traffic closure and recovery are determined. Finally, a resource allocation optimization model was developed to determine the number and location of resource allocation points which based on 19 hospitals to avoid the further spread of the virus. The results give a valuable reference for enhancing the resilience of urban transport systems and improving their performance in all phases.

Design and Implementation of Epidemic Prevention and Control Measures Recommendation System Based on K-means Clustering Algorithm

Aiming at the problem that it is difficult for countries to make appropriate judgment on the epidemic situation and what effective measures should be taken, this paper designed and implemented an epidemic prevention and control measures recommendation system based on K-means cluster analysis. Firstly, after normalizing the daily number of newly infected and cured people in various countries, the density based local anomaly factor algorithm was used to detect outliers. Excluding the impact of individual abnormal data on all the data, and then renormalizing the data, the data set was divided into three categories by K-means clustering method, which was respectively corresponded to the three stages of the epidemic situation. By comparing the clustering results of China with the actual situation, the three stages of transformation were roughly consistented with the actual situation. Finally, by referring to the epidemic prevention plan adopted by China in the same period, the epidemic prevention measures that should be taken in each stage were recommended. The results showed that the system has broad application prospects and practical significance for countries to quickly formulate effective control measures to control the spread of the epidemic. © 2022 ACM.

Analysis of public sentiment tendency in COVID-19 period based on GA-BiLSTM

As the Internet becomes the main source of information for the public, grasping the emotional polarity of online public opinion is particularly important for relevant departments to supervise online public opinion. In order to more accurately determine the emotional polarity of public opinion in the epidemic, this paper proposes a public sentiment analysis model based on Word2vec, genetic algorithm and Bi-directional Long Short-Term Memory (Bi-LSTM) algorithm. The Word2vec model converts the comment text into an n-dimensional vector, uses the Bi-LSTM algorithm to analyze the sentiment polarity, and uses the genetic algorithm to analyze the number of Bi-LSTM layers and the number of fully connected layers and the number of neurons in each layer of Bi-LSTM optimization. The experimental results show that the accuracy of the above model is compared with the accuracy of the Word2vec model and the LSTM model separately, and the accuracy is increased by 11.0% and 7.7%, respectively. © 2022 ACM.

WIDESPREAD OUTBREAK OF MIDDLE EAST RESPIRATORY SYNDROME CORONAVIRUS IN A CAMEL COHORT AND ASSOCIATED SPILLOVER TO HUMANS IN KENYA

Background: Middle East respiratory syndrome coronavirus (MERS-CoV) is an emerging coronavirus that is endemic in dromedary camels. Kenya's >3 million camels have high seroprevalence of antibodies against MERS-CoV, with scant evidence of human infection, possibly due to a lower zoonotic potential of Clade C viruses, predominantly found in African camels. Methods: Between April 2018-March 2020, we followed camels aged 0-24 months from 33 camel-keeping homesteads within 50Km of Marsabit town through collecting deep nasal swabs and documenting signs of illness in camels every two weeks. Swabs were screened for MERS-CoV by reverse transcriptase (RT)-polymerase chain reaction (PCR) testing and virus isolation performed on PCR positive samples with cycle threshold (CT) <20. Both the isolates and swab samples (CT <30) were subjected to whole genome sequencing. Human camel handlers were also swabbed and screened for symptoms monthly and samples tested for MERS-CoV by RT-PCR. Results: Among 243 calves, 68 illnesses were recorded in 58 camels (53.9%);50/68 (73.5%) of illnesses were recorded in 2019, and 39 (57.3%) were respiratory symptoms (nasal discharge, hyperlacrimation and coughing). A total of 124/4,702 camel swabs (2.6%) from 83 (34.2%) calves in 15 (45.5%) enrolled compounds were positive for MERS-CoV RNA. Cases were detected between May-September 2019 with three infection peaks, a similar period when three (1.1%) human PCR-positive but asymptomatic cases were detected among 262 persons handling these herds. Sequencing of camel specimens revealed a Clade C2 virus with identical 12 nucleotide deletion at the 3' end of OFR3 region and one nucleotide insertion at the 5' region but lacked the signature ORF4b deletions of other Clade C viruses. Interpretation: We found high levels of transmission of distinct Clade C MERS-CoV among camels in Northern Kenya, with likely spillover infection to humans. These findings update our understanding of MERS-CoV epidemiology in this region.

Data-Driven In-Crisis Community Identification for Disaster Response and Management

Since 2019, the world has been seriously impacted by the global pandemic, COVID-19, with millions of people adversely affected. This is coupled with a trend in which the intensity and frequency of natural disasters such as hurricanes, wildfires, and earthquakes have increased over the past decades. Larger and more diverse communities have been negatively influenced by these disasters and they might encounter crises socially and/or economically, further exacerbated when the natural disasters and pandemics co-occurred. However, conventional disaster response and management rely on human surveys and case studies to identify these in-crisis communities and their problems, which might not be effective and efficient due to the scale of the impacted population. In this paper, we propose to utilize the data-driven techniques and recent advances in artificial intelligence to automate the in-crisis community identification and improve its scalability and efficiency. Thus, immediate assistance to the in-crisis communities can be provided by society and timely disaster response and management can be achieved. A novel framework of the in-crisis community identification has been presented, which can be divided into three subtasks: (1) community detection, (2) in-crisis status detection, and (3) community demand and problem identification. Furthermore, the open issues and challenges toward automated in-crisis community identification are discussed to motivate future research and innovations in the area.

Management of the Pre-hospital Emergency Transport Strategy During the Novel Coronavirus Pneumonia Epidemic in Zhuzhou City, China

Objective : Summarize the experience of transporting patients in the pre-hospital emergency center of our hospital from January 20, 2020 to May 2020 during the outbreak of novel coronavirus pneumonia in Zhuzhou City, and formulate a series of transport strategics. Methods: During the novel coronavirus pneumonia epidemic, review the relevant experience of the medical staff and drivers in the pre-hospital emergency center of Zhuzhou Central Hospital to improve the procedures for the transfer of patients during the epidemic. Results: As of the time when patients with novel coronavirus pneumonia in our city are cleared, none of the medical staff in the pre-hospital emergency center of Zhuzhou Central Hospital has been infected, and the city's patients in need of pre-hospital emergency treatment have been treated in an orderly manner. In conjunction with our hospital's epidemic prevention and control expert team, combined with the actual situation in the region, we jointly formulated a series of transfer procedures for Zhuzhou Central Hospital to comply with the region during the epidemic. Conclusion: During the novel coronavirus pneumonia epidemic, all patients received by the pre-hospital emergency center of our hospital were transferred in a timely and safe manner, and a series of transfer procedures were developed.

Potential Tiger-to-Human Transmission of SARS-CoV-2 at a Tennessee Zoo: A One Health Approach to Outbreak Investigation

Background. Human-to-feline and airborne transmission among cats of Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) has been described, though documented feline-to-human transmission has not been reported. In October 2020, all 3 Malayan tigers at a Tennessee AZA accredited zoo were diagnosed with symptomatic SARS-CoV-2 infection. We investigated to determine source and prevent further transmission. Methods. Tiger nasal swab specimens were tested at the National Veterinary Services Laboratories (NVSL). An environmental assessment at the zoo was completed. We interviewed 18 staff who interacted with the tigers during the 2 weeks before animal symptom onset. Confirmed human cases were defined as persons testing positive for SARS-CoV-2 by RT-PCR during September 28-October 29, with tiger interaction during their 14-day incubation period. Interviewed staff had repeat SARSCoV-2 RT-PCR and serum IgG testing on October 29. Tigers and staff testing positive had specimens sent to CDC for genomic sequencing. Tiger sequences were compared phylogenetically with 30 geographically associated human cases collected within 2 weeks of the outbreak and > 200 background sequences from TN. Results. NVSL confirmed SARS-CoV-2 infection in all 3 tigers. Environmental assessment identified fencing between humans and animals allowing airflow and an open outdoor exhibit observation point above the habitat. Confirmed cases were identified in a tiger keeper and veterinary assistant;both developed symptoms after exposure to symptomatic tigers and one sample was genotyped. Staff did not report known contact with ill visitors. All staff were negative for SARS-CoV-2 IgG. The tigers and most temporally and geographically associated cases had genetic sequences in clade 20G and B.1.2. Tiger sequences were 3-6 single nucleotide polymorphisms different from the positive tiger keeper (Figure). Figure. Whole-genome phylogenetic analysis. Whole-genome phylogenetic analysis from a portion of clade 20G showing divergence estimates from SARS-CoV-2 Wuhan-Hu-1 reference genome with sequences from humans living in Tennessee and Malayan tigers sampled during the outbreak investigation in October 2020. Sequence analysis showed 3-6 single nucleotide polymorphisms (SNPs) differences between one human tiger keeper and all three tiger sequences. Differences are indicated by one-step edges (lines) between colored dots (individual SARS-CoV-2 sequenced infections). Numbers indicate unique sequences. Note not all analyzed sequences are shown in this figure. Conclusion. Using a One Health approach, we concluded the index tiger was likely infected via transmission from an ill visitor at an exhibit observation point or unidentified asymptomatic staff. Infection spread to the other 2 tigers and tigerto-human transmission to 2 staff is possible thereafter. The zoo was advised on infection control practices for humans and animals, and no additional cases were identified.

An explainable sentiment prediction model based on the portraits of users sharing representative opinions in social sensors

"Social sensors" refer to those who provide opinions through electronic communication channels such as social networks. There are two major issues in current models of sentiment analysis in social sensor networks. First, most existing models only analyzed the sentiment within the text but did not analyze the users, which led to the experimental results difficult to explain. Second, few studies extract the specific opinions of users. Only analyzing the emotional tendencies or aspect-level emotions of social users brings difficulties to the analysis of the opinion evolution in public emergencies. To resolve these issues, we propose an explainable sentiment prediction model based on the portraits of users sharing representative opinions in social sensors. Our model extracts the specific opinions of the user groups on the topics and fully considers the impacts of their diverse features on sentiment analysis. We conduct experiments on 51,853 tweets about the "COVID-19" collected from 1 May 2020 to 9 July 2020. We build users' portraits from three aspects: attribute features, interest features, and emotional features. Six machine learning algorithms are used to predict emotional tendency based on users' portraits. We analyze the influence of users' features on the sentiment. The prediction accuracy of our model is 64.88%.

Real Time Face Mask Detection System using Transfer Learning with Machine Learning Method in the Era of Covid-19 Pandemic

The rapid development of computer vision has attracted more attention to the global epidemic Covid-19 to enable human-computer interaction and improve public health services. Due to the rapid spread of the (Covid-19), various countries are facing a major health crisis. According to the World Health Organization (WHO) an effective way to protect people from Covid-19 is to wear medical masks in public areas. It is very difficult to manually monitor people in public places and detect the face mask in the video. which is mainly because the mask itself acts as an obstruction to the face detection algorithm, because there are no face signs in the mask area. Therefore, automatic face mask detection system helps authorities to identify people who may be susceptible to infections disease. This research aims to use deep learning to automatically detect face masks in videos. The proposed framework consists of two components. The first component is designed for face detection and tracking using OpenCV and machine learning, and in the second component, these facial frames are then processed into our proposed deep transfer learning model MobileNetV2 to identify the mask area. The proposed framework was tested on different videos and images using the smartphone camera. The purpose is to achieve high-precision real-time detection and classification. The model achieved 99.2% accuracy during training and 99.8% validation accuracy. which is better than other recently proposed methods. Experimental results show that the work proposed in this paper can effectively recognize face masks with multiple targets and provide effective personnel surveillance. This research is useful for controlling the spread of the virus and preventing exposure to the virus. © 2021 IEEE.