ABSTRACT
Although many AI-based scientific works regarding chest X-ray (CXR) interpretation focused on COVID-19 diagnosis, fewer papers focused on other relevant tasks, like severity estimation, deterioration, and prognosis. The same holds for explainable decisions to estimate COVID-19 prognosis as well. The international hackathon launched during Dubai Expo 2020, aimed at designing machine learning solutions to help physicians formulate COVID-19 patients' prognosis, was the occasion to develop a machine learning model capable of predicting such prognoses and justifying them through interpretable explanations. The large hackathon dataset comprised subjects characterized by their CXR and numerous clinical features collected during triage. To calculate the prognostic value, our model considered both patients' CXRs and clinical features. After automatic pre-processing to improve their quality, CXRs were processed by a Deep Learning model to estimate the lung compromise degree, which has been considered as an additional clinical feature. Original clinical parameters suffered from missing values that were adequately handled. We trained and evaluated multiple models to find the best one and fine-tune it before the inference process. Finally, we produced novel explanations, both visual and numerical, to justify the model predictions. Ultimately, our model processes a CXR and several clinical data to estimate a patient's prognosis related to the COVID-19 disease. It proved to be accurate and was ranked second in the final rankings with 75%, 73.9%, and 74.4% in sensitivity, specificity, and balanced accuracy, respectively. In terms of model explainability, it was ranked first since it was agreed to be the most interpretable by health professionals. © 2023 SPIE.
ABSTRACT
Classifying Covid-19 and Pneumonia is one of the most important and challenging tasks in the field of the medical sector since manual classification with human assistance can lead to incorrect prediction and diagnosis. Additionally, it is a difficult operation when there is a lot of data that need to be analyzed thoroughly. Due to the similarity in symptoms as well as in chest X-ray images of Covid-19 and Pneumonia diseases, it is difficult to distinguish those. The study presents a technological solution to build a mixed-data model using customized neural networks to discriminate between Covid-19 and Pneumonia. The proposed method is applied to the chest X-ray images and symptoms of patients of Covid-19 and Pneumonia. This helps to perform immediate prediction of Covid-19 and Pneumonia providing fast and specialized treatment to the patients appropriately. This prediction also helps the radiologist or doctors in making quick decisions. In this work, imaging data (such as Chest X-ray images) and text data (such as disease symptoms like cough, body pain, short breathing, fever, etc.) are taken for detecting Covid-19, Pneumonia and Normal patients. Data Synthesis is carried out due to the unavailability of mixed data and it has created dataset of 450 entries of Covid-19, Normal and Pneumonia cases. The goal is to design a system that accurately classifies Covid19, Pneumonia, and Normal patients by utilizing convolutional neural networks (CNN) and multi-layer perceptron (MLP) algorithms. An accuracy of 93.33% is obtained for the mixed-data model using a deep neural network, that is designed by combining custom CNN and MLP architectures. © 2022 IEEE.
ABSTRACT
To deal with the COVID-19 pandemic, schools at all levels insist on "classes suspended but learning continues"and actively implement online teaching. Different from the planned shift from offline to online education, COVID-19 caused online teaching to be highly sudden and emergent, producing different learning outcomes from offline teaching. Therefore, it is critical to analyze the epidemic's impact on students' learning outcomes. However, prior studies only focus on statistical data of the learning process, such as students' test scores or homework completion, rather than comments posted on social media. This paper explores the impact of COVID-19 on students' online exams by identifying potential topics during the final exam period. We first collect and preprocess a huge number of Weibo posts with natural language processing methods. Then, we explore related topics via LDA (Latent Dirichlet Allocation) model. Finally, the extensive experimental results demonstrate that our findings for the 16 topic groups have significant roles in exploring students' attitudes towards online exams and exam cheating. Furthermore, we found that the overall affective attitudes of users' postings tended to be negative. © 2022 IEEE.
ABSTRACT
This article presents the analysis of the demand and the characterization of mobility using public transportation in Montevideo, Uruguay, during the COVID-19 pandemic. A urban data-analysis approach is applied to extract useful insights from open data from different sources, including mobility of citizens, the public transportation system, and COVID cases. The proposed approach allowed computing significant results to determine the reduction of trips caused by each wave of the pandemic, the correlation between the number of trips and COVID cases, and the recovery of the use of the public transportation system. Overall, results provide useful insights to quantify and understand the behavior of citizens in Montevideo, regarding public transportation during the COVID-19 pandemic. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
The outbreak of the coronavirus disease in Nigeria and all over the world in 2019/2020 caused havoc on the world's economy and put a strain on global healthcare facilities and personnel. It also threw up many opportunities to improve processes using artificial intelligence techniques like big data analytics and business intelligence. The need to speedily make decisions that could have far-reaching effects is prompting the boom in data analytics which is achieved via exploratory data analysis (EDA) to see trends, patterns, and relationships in the data. Today, big data analytics is revolutionizing processes and helping improve productivity and decision-making capabilities in all aspects of life. The large amount of heterogeneous and, in most cases, opaque data now available has made it possible for researchers and businesses of all sizes to effectively deploy data analytics to gain action-oriented insights into various problems in real time. In this paper, we deployed Microsoft Excel and Python to perform EDA of the covid-19 pandemic data in Nigeria and presented our results via visualizations and a dashboard using Tableau. The dataset is from the Nigeria Centre for Disease Control (NCDC) recorded between February 28th, 2020, and July 19th, 2022. This paper aims to follow the data and visually show the trends over the past 2 years and also show the powerful capabilities of these data analytics tools and techniques. Furthermore, our findings contribute to the current literature on Covid-19 research by showcasing how the virus has progressed in Nigeria over time and the insights thus far. © 2022 IEEE.
ABSTRACT
Development in technology has led to a spike in sharing of opinions about different subjects on social media, for instance, movie or product reviews. Unprecedented COVID-19 led to forced isolation and affected mental health negatively. This paper introduces a system to detect users' emotions and mental states based on provided input. Among the different data sources available on social media, real-time Twitter data is used in this analysis. Sentiment analysis can be used as a tool at various levels, right from individual to organizational development. Deep learning algorithms like LSTM and CNN lay the foundation of this system. Python libraries and Google APIs are used to add functionalities. Earlier studies only focused on detecting emotions, whereas the proposed system provides the user with a graphical analysis of detected emotions and apt suggestions like motivational quotes or videos. The system accepts multilingual text input, speech, or video input. The scope of this system is not restricted to COVID-19 related texts. This research will assist individuals and businesses and aid future development. © 2022 IEEE.
ABSTRACT
This study presents a detailed survey of different works related to sentiment analysis. The COVID-19 pandemic and its impact on people's mental health act as the driving force behind this survey. The survey can help study sentiment analysis and approaches taken in many studies to detect human emotions via advanced technology. It can also help in improving present systems by finding loopholes and increasing their accuracy. Various lexicon and ML-based systems and models like Word2Vec and LSTM were studied in the surveyed papers. Some of the current and future directions highlighted were Twitter sentiment analysis, review-based market analysis, determining changing behavior and emotions in a given time period, and detecting the mental health of employees, and students. This survey provides details related to trends and topics in sentiment analysis and an in-depth understanding of various technologies used in different studies. It also gives an insight into the wide variety of applications related to sentiment analysis. © 2022 IEEE.
ABSTRACT
Social media have the potential to provide timely information about emergency situations and sudden events. However, finding relevant information among the millions of posts being added every day can be difficult, and in current approaches developing an automatic data analysis project requires time and technical skills. This work presents a new approach for the analysis of social media posts, based on configurable automatic classification combined with Citizen Science methodologies. The process is facilitated by a set of flexible, automatic and open-source data processing tools called the Citizen Science Solution Kit. The kit provides a comprehensive set of tools that can be used and personalized in different situations, particularly during natural emergencies, starting from images and text contained in the posts. The tools can be employed by citizen scientists for filtering, classifying, and geolocating the content with a human-in-the-loop approach to support the data analyst, including feedback and suggestions on how to configure the automated tools, and techniques to gather inputs from citizens. Using flooding scenario as a guiding example, this paper illustrates the structure and functioning of the different tools proposed to support citizens scientists in their projects, and a methodological approach to their use. The process is then validated by discussing three case studies based on the Albania earthquake of 2019, the Covid-19 pandemic, and the Thailand floods of 2021. The results suggest that a flexible approach to tools composition and configuration can support a timely setup of an analysis project by citizen scientists, especially in case of emergencies in unexpected locations. © 2013 IEEE.
ABSTRACT
There is a great challenge to deal with prediction of an epidemic or pandemic in the future through artificial intelligence or state-of-art technology. This is evident in the case of pandemic happened from January 2020 which is a result of corona virus. In early stages of covid-19 caused by corona virus, the symptoms are not severe and mostly cured through self-medication. In this situation, estimating the real spread based on the reports from various hospitals might be misleading. There might be lot of variation in the reports based on different types of measurements performed, and the tests conducted on only the symptomatic patients. In spite of all these constraints, a huge amount of covid-19 related data is published since 3 years and also updated on a daily basis. This serves as a motivation to consider various mathematical models to predict the course of change in an epidemic and result in effective control strategies. The challenge is to predict the peak and end of the epidemic together with its evolution through available incomplete data and intrinsic complexity. In this paper, time series models are proposed to analyze corona spread data and analyzing its impact based on gender, age and geographical location. The proposed algorithm leverages machine learning models to predict number of corona cases in the future. An early detection of spread of corona would help in stopping community transmission and this serves a major motivation for this research. ARIMA model and Recurrent Neural Networks (RNN) based LSTM model perform way better than the machine learning models based on regression and decision trees. © 2022 IEEE.
ABSTRACT
Social media, like Twitter, is a data repository, and people exchange views on global issues like the COVID-19 pandemic. Social media has been shown to influence the low acceptance of vaccines. This work aims to identify public sentiments concerning the COVID-19 vaccines and better understand the individual's sensitivities and feelings that lead to achievement. This work proposes a method to analyze the opinion of an individual's tweet about the COVID-19 vaccines. This paper introduces a sigmoidal particle swarm optimization (SPSO) algorithm. First, the performance of SPSO is measured on a set of 12 benchmark problems, and later it is deployed for selecting optimal text features and categorizing sentiment. The proposed method uses TextBlob and VADER for sentiment analysis, CountVectorizer, and term frequency-inverse document frequency (TF-IDF) vectorizer for feature extraction, followed by SPSO-based feature selection. The Covid-19 vaccination tweets dataset was created and used for training, validating, and testing. The proposed approach outperformed considered algorithms in terms of accuracy. Additionally, we augmented the newly created dataset to make it balanced to increase performance. A classical support vector machine (SVM) gives better accuracy for the augmented dataset without a feature selection algorithm. It shows that augmentation improves the overall accuracy of tweet analysis. After the augmentation performance of PSO and SPSO is improved by almost 7% and 5%, respectively, it is observed that simple SVM with 10-fold cross-validation significantly improved compared to the primary dataset. © 2023 Tech Science Press. All rights reserved.
ABSTRACT
School lecture halls are often designed as confined spaces. During the period of COVID-19, indoor ventilation has played an even more important role. Considering the economic reasons and the immediacy of the effect, the natural ventilation mechanism becomes the primary issue to be evaluated. However, the commonly used CO2 tracer gas concentration decay method consumes a lot of time and cost. To evaluate the ventilation rate fast and effectively, we use the common methods of big data analysis - Principal Component Analysis (PCA), K-means and linear regression to analyze the basic information of the lecture hall to explore the relation between variables and air change rate. The analysis results show that the target 37 lecture halls are divided into two clusters, and the measured 11 lecture halls contributed 64.65%. When analyzing the two clusters separately, there is a linear relation between the opening area and air change rate (ACH), and the model error is between 6% and 12%, which proves the feasibility of the basic information of the lecture hall by calculating the air change rate. © 2023 Elsevier Ltd
ABSTRACT
The advance of digital technologies such as big data, cloud computing, and artificial intelligence ushers in the digital era for modern societies. Digital IT innovation plays an increasingly important role in helping supply chains recover from disruptions due to disastrous events like the COVID-19 outbreak. Nevertheless, there is a lack of systematic literature review on the phenomenon. As such an attempt, this paper explores the role of digital technology innovation in enhancing supply chain resilience and answers this question through a literature review and summarizes six dimensions of supply chain resilience, which provides some theoretical guidance for subsequent studies. © 2022 IEEE.
ABSTRACT
The lockdown caused by the COVID-19 epidemic has led to using smartphones and decreasing physical activity in the world. It is known that increased screen time and decreased physical activity have bad effects on physical and mental health. However, few studies investigate the influence of screen time on the amount of exercise. By analyzing the influence, exercise promotion services can be improved. Therefore, in this study, we challenge to clarify the relationship between exercise and the screen time. Using a machine learning method, we verify the influence importance of screen time on the amount of exercise. We collect the data on smartphone screen time, tablet screen time, steps, and sleep score from a male college student. In addition, we gather weather of the location, and weekdays/weekends data during our experiment period. To analyze the influence, Gradient Boosting Decision Tree (GBDT) is used. GBDT is a kind of decision tree-based method, and it can show the importance of explainable variables. As a result, the variables that were more important for exercise were, in order of importance, total screen time (total screen times of his smartphone and tablet), screen time of smartphone, and sleep score. The result showed that using electronic devices such as smartphones and tablets influence on the exercise. Moreover, the sleep score also had an influence. © 2022 IEEE.
ABSTRACT
Our aim is to study the contribution of telework to resilience during the pandemic. The research question is: how does telework affect individual and collective resilience during this crisis? We analyse the results from five online surveys from March 2020 to February 2021. The corpus results from the compilation of five different sources: written reports, two narrative surveys, a quantitative survey, and three focus groups. Thus, the transcription of 1,299 managers and specialists is studied following the textual data analysis methods. Our findings indicate that the contribution of telework differs whether the resilience is individual or collective. The process of resilience is also dynamic and we propose to distinguish three phases: preventive resilience (before the disaster), reactive resilience (during the disaster) and curative resilience (after the disaster). We use the results of the resilience study to discuss implications for the development of telework as a digital tool and practice. © 2022 IEEE.
ABSTRACT
In this study, sentiment analysis was conducted on the data of the Covid-19 epidemic process from the official twitter account of the Republic of Turkey Fahrettin Koca, Minister of Health, @drfahrettinkoca (SO) and the Twitter account of the @WHO (World Health Organization). First of all, twitter data was obtained and necessary arrangements were made for analysis. Then, tweets were shown with a word cloud and it was determined which words were used more frequently. Afterwards, sentiment analysis was performed on the data using the TextBlob library. In addition, it has been found out which subjects are focused on tweets sent from SO and @WHO (World Health Organization) accounts with the LDA algorithm. It has been seen that positive tweets were sent from both accounts, giving positive messages to the society. © 2022 IEEE.
ABSTRACT
Given a large, semi-infinite collection of co-evolving epidemiological data containing the daily counts of cases/deaths/recovered in multiple locations, how can we incrementally monitor current dynamical patterns and forecast future behavior? The world faces the rapid spread of infectious diseases such as SARS-CoV-2 (COVID-19), where a crucial goal is to predict potential future outbreaks and pandemics, as quickly as possible, using available data collected throughout the world. In this paper, we propose a new streaming algorithm, EPICAST, which is able to model, understand and forecast dynamical patterns in large co-evolving epidemiological data streams. Our proposed method is designed as a dynamic and flexible system, and is based on a unified non-linear differential equation. Our method has the following properties: (a) Effective: it operates on large co-evolving epidemiological data streams, and captures important world-wide trends, as well as location-specific patterns. It also performs real-time and long-term forecasting;(b) Adaptive: it incrementally monitors current dynamical patterns, and also identifies any abrupt changes in streams;(c) Scalable: our algorithm does not depend on data size, and thus is applicable to very large data streams. In extensive experiments on real datasets, we demonstrate that EPICAST outperforms the best existing state-of-the-art methods as regards accuracy and execution speed. © 2022 ACM.
ABSTRACT
Outbreaks of the COVID-19 pandemic, caused by the SARS-CoV-2 virus, have led to the creation of social distancing and lockdown policies to reduce the spread of the virus. Consequently, public/private transportation services, schools, workplaces, and retail stores' operations were disrupted. We gather user mobility reports worldwide to learn impacts of early COVID-19 outbreaks on human mobility patterns and trends. Building time series of six types of activities tracked in the Google Community Mobility Reports (CMR), we develop visualization tools and interactive dashboards for linking mobility and COVID-19 infection data at different levels (from county- and state-level in the US, to country level for the rest of the world). We show that the relationship between mobility and COVID-19 infection changes over time, and therefore the stage of the pandemic is essentially important for understanding how containment policies can affect infections and deaths caused by the COVID-19 pandemic. © 2022 IISE Annual Conference and Expo 2022. All rights reserved.
ABSTRACT
The abundance of available information on social networks can provide invaluable insights into people’s responses to health information and public health guidance concerning COVID-19. This study examines tweeting patterns and public engagement on Twitter, as forms of social networks, related to public health messaging in two U.S. states (Washington and Louisiana) during the early stage of the pandemic. We analyze more than 7M tweets and 571K COVID-19-related tweets posted by users in the two states over the first 25 days of the pandemic in the U.S. (Feb. 23, 2020, to Mar. 18, 2020). We also qualitatively code and examine 460 tweets posted by selected governmental official accounts during the same period for public engagement analysis. We use various methods for analyzing the data, including statistical analysis, sentiment analysis, and word usage metrics, to find inter-and intra-state disparities of tweeting patterns and public engagement with health messaging. Our findings reveal that users inWashington were more active on Twitter than users in Louisiana in terms of the total number and density of COVID-19-related tweets during the early stage of the pandemic. Our correlation analysis results for counties or parishes show that the Twitter activities (tweet density, COVID-19 tweet density, and user density) were positively correlated with population density in both states at the 0.01 level of significance. Our sentiment analysis results demonstrate that the average daily sentiment scores of all and COVID-19-related tweets inWashington were consistently higher than those in Louisiana during this period. While the daily average sentiment scores of COVID-19-related tweets were in the negative range, the scores of all tweets were in the positive range in both states. Lastly, our analysis of governmental Twitter accounts found that these accounts’messages were most commonly meant to spread information about the pandemic, but that users were most likely to engage with tweets that requested readers take action, such as hand washing. Author
ABSTRACT
Analysis of data sets that may be changing often or in real-time, consists of at least three important synchronized components: i) figuring out what to infer (objectives), ii) analysis or computation of those objectives, and iii) understanding of the results which may require drill-down and/or visualization. There is considerable research on the first two of the above components whereas understanding actionable inferences through visualization has not been addressed properly. Visualization is an important step towards both understanding (especially by non-experts) and inferring the actions that need to be taken. As an example, for Covid-19, knowing regions (say, at the county or state level) that have seen a spike or are prone to a spike in the near future may warrant additional actions with respect to gatherings, business opening hours, etc. This paper focuses on a modular and extensible architecture for visualization of base as well as analyzed data. This paper proposes a modular architecture of a dashboard for user interaction, visualization management, and support for complex analysis of base data. The contributions of this paper are: i) extensibility of the architecture providing flexibility to add additional analysis, visualizations, and user interactions without changing the workflow, ii) decoupling of the functional modules to ease and speed up development by different groups, and iii) supporting concurrent users and addressing efficiency issues for display response time. This paper uses Multilayer Networks (or MLNs) for analysis. To showcase the above, we present the architecture of a visualization dashboard, termed CoWiz++ (for Covid Wizard), and elaborate on how web-based user interaction and display components are interfaced seamlessly with the back-end modules. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
The new crown epidemic is raging around the world, especially in Tokyo, Japan. After the Olympics, the situation of the new crown epidemic is not optimistic. At the same time, due to the emergence of more unstable factors, the number of newly confirmed and death cases is becoming more and more difficult to predict, which poses great challenges to the prevention and control of the epidemic. An effective forecasting method is urgently needed. In order to deal with the unpredictable Tokyo coronavirus epidemic, this article analyzes the existing coronavirus confirmed and death data and predicts the future trend of the coronavirus epidemic. This article first uses the ARIMA-GARCH model to make predictions, and obtains more accurate prediction results. Furthermore, this article uses the SIR model for fitting and prediction, and finally provides guidance on Tokyo's future anti-epidemic policy. © COPYRIGHT SPIE.