Mobilisation practices during the SARS-CoV-2 pandemic: A retrospective analysis (MobiCOVID).

BACKGROUND: Corona Virus Disease 2019 (COVID-19) patients display risk factors for intensive care unit acquired weakness (ICUAW). The pandemic increased existing barriers to mobilisation. This study aimed to compare mobilisation practices in COVID-19 and non-COVID-19 patients. METHODS: This retrospective cohort study was conducted at Charité-Universitätsmedizin Berlin, Germany, including adult patients admitted to one of 16 ICUs between March 2018, and November 2021. The effect of COVID-19 on mobilisation level and frequency, early mobilisation (EM) and time to active sitting position (ASP) was analysed. Subgroup analysis on COVID-19 patients and the ICU type influencing mobilisation practices was performed. Mobilisation entries were converted into the ICU mobility scale (IMS) using supervised machine learning. The groups were matched using 1:1 propensity score matching. RESULTS: A total of 12,462 patients were included, receiving 59,415 mobilisations. After matching 611 COVID-19 and non-COVID-19 patients were analysed. They displayed no significant difference in mobilisation frequency (0.4 vs. 0.3, p = 0.7), maximum IMS (3 vs. 3; p = 0.17), EM (43.2% vs. 37.8%; p = 0.06) or time to ASP (HR 0.95; 95% CI: 0.82, 1.09; p = 0.44). Subgroup analysis showed that patients in surge ICUs, i.e., temporarily created ICUs for COVID-19 patients during the pandemic, more commonly received EM (53.9% vs. 39.8%; p = 0.03) and reached higher maximum IMS (4 vs. 3; p = 0.03) without difference in mobilisation frequency (0.5 vs. 0.3; p = 0.32) or time to ASP (HR 1.15; 95% CI: 0.85, 1.56; p = 0.36). CONCLUSION: COVID-19 did not hinder mobilisation. Those treated in surge ICUs were more likely to receive EM and reached higher mobilisation levels.

EFFICIENT COVID-19 DISEASE DIAGNOSIS BASED ON COUGH SIGNAL PROCESSING AND SUPERVISED MACHINE LEARNING

The spread of the coronavirus has claimed the lives of millions worldwide, which led to the emergence of an economic and health crisis at the global level, which prompted many researchers to submit proposals for early diagnosis of the coronavirus to limit its spread. In this work, we propose an automated system to detect COVID-19 based on the cough as one of the most important infection indicators. Several studies have shown that coughing accounts for 65% of the total symptoms of infection. The proposed system is mainly based on three main steps: first, cough signal detection and segmentation;second, cough signal extraction;and third, three techniques of supervised machine learning-based classification: Support Vector Machine (SVM), K-Nearest Neighbours (KNN), and Decision Tree (DT). Our proposed system showed high performance through good accuracy values, where the best accuracy for classifying female coughs was 99.6% using KNN and 88% for males using SVM. © 2022 by the Authors.

Semi-Supervised Machine Learning for Analyzing COVID-19 Related Twitter Data for Asian Hate Speech

The COVID-19 pandemic left a lot of people sick, tired, and frustrated. Many people expressed their feelings on social media through comments and posts. Detecting hate speech on social media is important to help reduce the spread of racist comments. Machine learning algorithms can be used to classify hate speech. In our experiments, we implement semi-supervised machine learning algorithms to classify Twitter data. We used a count vectorizer as the feature and a support vector machine (SVM) classifier to classify COVID-19 related Twitter data while changing the amount of labeled data available. We found that self-training semi-supervised machine learning has similar effectiveness to supervised learning when there is significantly less training data available. © 2022 IEEE.

Supervised Machine Learning Strategy for detection of covid19 patients

The current severe acute respiratory syndrome corona virus 2 (SARS-CoV-2) public health catastrophe, both human lives have been lost and the economy has disrupted severely the current scenario. In this paper, we develop a detection module using a series of steps that involves pre-processing, feature extraction and detection of covid-19 patients based on the images collected from the computerized tomography (CT) images. The images are initially pre-processed and then the features are extracted using Gray Level Co-occurrence Matrix (GLCM) and then finally classified using back propagation neural network (BPNN). The simulation is conducted to test the efficacy of the model against various CT image datasets of numerous patients. The results of simulation shows that the proposed method achieves higher detection rate, and reduced mean average percentage error (MAPE) than other existing methodologies. © 2023 IEEE.

Career Path Prediction System Using Supervised Learning Based on Users' Profile

In the past few years, technology has changed drastically and due to COVID-19 pandemic, people spend more time on screen. The use of social media platforms has also been increased and this affects the human mind and decision taking ability. Online career counseling is largely supported these days and hence this paper proposes an online career prediction system using supervised machine learning based on the user's profile. This research attempted to develop a model for the user which predicts the career path in a precise manner and gives actionable feedback and career recommendations to encourage them to make significant career judgments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

Ethnic Differences in Response to COVID-19: A Study of American-Asian and Non-Asian College Students.

Asian American students have experienced additional physical and emotional hardships associated with the COVID-19 pandemic due to increased xenophobic and anti-Asian discrimination. This study investigates different coping patterns and risk factors affecting Asian and non-Asian college students in response to COVID-19 challenges by studying the differences in their responses within four domains after the onset of the pandemic: academic adjustment, emotional adjustment, social support, and discriminatory impacts related to COVID-19. We first employed a machine learning approach to identify well-adjusted and poorly adjusted students in each of the four domains for the Asian and non-Asian groups, respectively. Next, we applied the SHAP method to study the principal risk factors associated with each classification task and analyzed the differences between the two groups. We based our study on a proprietary survey dataset collected from U.S. college students during the initial peak of the pandemic. Our findings provide insights into the risk factors and their directional impact affecting Asian and non-Asian students' well-being during the pandemic. The results could help universities establish customized strategies to support these two groups of students in this era of uncertainty. Applications for international communities are discussed.

Stress Detection on Social Network: Public Mental Health Surveillance: Public mental health surveillance

Many nations of the world struggle with the COVID-19 pandemic, as the disease causes wide sweeping changes to society and the economy. One of the consequences of the pandemic is its effect on mental health stress. Gauging stress levels at scale is challenging to implement, as traditional methods require administrative labour and time. However, a combination of supervised Machine Learning (ML) and social media analytics could provide a faster and aggregated way to detect the stress levels of a population. This study investigates the potential clinical usage of ML practices for detecting stress in Twitter content, as a quantitative measure of stress at scale. The stress scores obtained by the models will be compared to the COVID-19 timeline of daily new cases. © 2023 ACM.

Feature Selection For High Dimensional Data Using Supervised Machine Learning Techniques

In recent years, feature selection has become an increasingly active field of data science and machine learning research. Most of the datasets that are being used nowadays for various machine learning tasks consist of thousands of features (columns), which make them extremely complex and difficult to work with. In this paper, we propose a feature selection methodological pipeline that can be used to reduce the complexity of high dimensional datasets through the elimination of redundant and/or non-informative features as well as to improve the performance of machine learning models which are trained on high dimensional datasets. The proposed method has been applied to high-dimensional biomedical data and compared against a classic filter-based feature selection algorithm. Specifically, the method was applied to gene expression profiles of a single-cell RNA-seq dataset from healthy and infected by covid-19 human samples. © 2022 IEEE.

Classification And Errors Analysis of COVID-19 Using Supervised Machine Learning Algorithm and Visualisation

During pandemic many people died as a result of the covid-19 sickness, which appeared in 2019 and spread over the world. The objective of research work is to wards the occurrence of COVID to improve classification accuracy and threshold curve predictions on real-life dataset for Receiver Operator Characteristics (ROC) value. This paper goals the real-life COVID patients from the five countries to test the experiment. The proposed methodology involves of two steps;used Weka for calculating the accuracy by applying Decision Table machine learning classifier and compare the results of all the five countries, secondly, the improvement in ROC value in terms of initial care predictions by area under ROC analysis. For our COVID dataset has 209 instances and 16 attributes, Weka has performed on the number of training instances are 184, number of Rules applied is 20, search direction has been applied in forward direction, total number of subsets evaluated is 96, merit of best subset found is 82.609 and time taken to build model is 0. 06 seconds. One advantage of our suggested mode list hat it keeps the original data intact, ensuring experiment quality. A further advantage is that the model can be used with additional data sets to produce the highest accuracy and ROC analysis out comes.Copyright © 2022, Anka Publishers. All rights reserved.

Investigating dynamic relations between factual information and misinformation: Empirical studies of tweets related to prevention measures during COVID-19

During COVID-19, misinformation on social media has affected people's adoption of appropriate prevention behaviors. Although an array of approaches have been proposed to suppress misinformation, few have investigated the role of disseminating factual information during crises. None has examined its effect on suppressing misinformation quantitatively using longitudinal social media data. Therefore, this study investigates the temporal correlations between factual information and misinformation, and intends to answer whether previously predominant factual information can suppress misinformation. It focuses on two prevention measures, that is, wearing masks and social distancing, using tweets collected from April 3 to June 30, 2020, in the United States. We trained support vector machine classifiers to retrieve relevant tweets and classify tweets containing factual information and misinformation for each topic concerning the prevention measures' effects. Based on cross-correlation analyses of factual and misinformation time series for both topics, we find that the previously predominant factual information leads the decrease of misinformation (i.e., suppression) with a time lag. The research findings provide empirical understandings of dynamic relations between misinformation and factual information in complex online environments and suggest practical strategies for future misinformation management during crises and emergencies. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

A Comparative Study of Supervised Machine Learning Algorithms for Fake Review Detection

The behavior of shopping has shifted into online shopping. Especially after Coronavirus Disease of 2019 (COVID-19), people choose online shopping rather than going to the market for economic and hygienic reasons. Reviews help the seller to make customers trust their products, but since some sellers are not honest, they use fake reviews to help boost their products. Fake reviews are commonly generated randomly by a computer bot or someone not using the product. Some researchers are already working on fake review detection to help this problem using many methods. In this paper, we compared three supervised machine learning algorithms: Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF). By preprocessing the data and using the Term Frequency-Inverse Document Frequency (TF-IDF) feature, we begin the experiment process without tuning. We apply the tuning parameters to each algorithm for the other experiments using 5-fold cross-validation. The result showed that SVM algorithms outperform the best algorithms of the three before and after tuning, with 88.89% and 89.77%, respectively. © 2022 IEEE.

Prediction of Unemployment using Machine Learning Approach

Unemployment is a circumstance which arises when people above a specific age are not engaged in any kind of activities which contribute to the economic welfare of the individual and country. Unemployment is becoming a rising concern which is making the daily life of people difficult. Unemployment causes poverty and depression among the citizens. Nowadays there are different opportunities in different sectors. But people are not aware of those opportunities. Different states are there where there is a lack of skilled labour whereas many states are there that have skilled labour but less opportunities. Another reason for unemployment since 2020 is the COVID-19 pandemic. We have selected this topic to spread awareness among the citizens. This work attempts to detect the states of India which are in serious need of increasing employment opportunities. We have applied the concept of Supervised Machine Learning algorithms to detect the states with the lowest employment rate. The data visualization gives a better picture of the trends in unemployment rate over years. There has been a use of different popular algorithms like Logistic Regression, Support Vector Machine, K-nearest neighbors (kNN) Algorithm and Decision Tree. In the end we have tried to find the algorithm which is going to give us more accuracy so that necessary steps can be taken for the employment of the eligible and deserving people. © 2022 IEEE.

A Study to Analyse Covid-19 Outbreak Using Multiple Linear Regression: A Supervised Machine Learning Approach

Introduction: Globally, COVID-19 have impacted people's quality of life Machine learning have recently be-come popular for making predictions because of their precision and adaptability in identifying diseases. This study aims to identify significant predictors for daily active cases and to visualise trends in daily active, positive cases, and immunisations. Material and methods: This paper utilized secondary data from Covid-19 health bulletin of Uttarakhand and multiple linear regression as a part of supervised machine learning is performed to analyse dataset. Results: Multiple Linear Regression model is more accurate in terms of greater score of R2 (=0.90) as com-pared to Linear Regression model with R2 =0.88. The daily number of positive, cured, deceased cases are significant predictors for daily active cases (p <0.001). Using time series linear regression approach, cumulative number of active cases is forecasted to be 6695 (95% CI: 6259-7131) on 93rd day since 18 Sep 2022, if similar trend continues in upcoming 3 weeks in Uttarakhand. Conclusion: Regression models are useful for forecasting COVID-19 instances, which will help governments and health organisations address this pandemic in future and establish appropriate policies and recommen-dations for regular prevention. © 2023 National Journal of Community Medicine.

COVID-19 Future Forecasting Using Machine Learning Models

Covid-19 is a very infectious virus. According to World Health Organization (WHO), millions of individuals have been diagnosed with Covid-19 since then, and at least a million have died as the virus has expanded dramatically. While most of the news on this front is scary, technology is helping to pave the path through this crisis. Manual forecasting is a difficult challenge for humans due to its large scale and complexity. Machine Learning (ML) techniques can effectively predict Covid-19 infected patients. There are a lot of study that have been developed to predict and forecast the future number of cases affected by Covid-19. In this area, our forecasting can be tackled as a problem of supervised learning. Supervised ML is very popular regression methods due to its simplicity to be interpreted by Humans. In this paper, we use two datasets to predict the symptoms through two different types of regression algorithms (single and multiple regression), the ML algorithms are LR, SVM, LASSO, ES and Polynomial regression, for the multiple regression we used LR, SVM and LASSO. The obtained results validate that for the single regression the Exponential Smoothing (ES) outperforms other machine learning approaches like Linear Regression (LR) and LASSO in terms of R-Square, Adjusted R-Square, Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE). The same accuracy is observed for the models used in the multiple regression. © 2022 IEEE.

Detection of Covid-19 Virus using Supervised Machine Learning Algorithms

Due to the continuous increase of Covid-19 infections as a global pandemic, it became necessary to detect it to avoid the damage caused by the spread of the infection. Artificial Intelligence (AI) techniques such as machine learning and deep learning have an important and effective role in the medical field applications like the classification of medical images and the detection of many diseases. In this article, we propose the use of several supervised machine learning classifiers for Covid-19 virus detection using chest x-ray (CXR) images. Five supervised classifiers are used: Support Vector Machines (SVM), Naive Bayes (NB), K-Nearest Neighbors (KNN), Logistic Regression (LR) and Artificial Neural Network (ANN). A standard dataset of 1824 CXR images are used for training and testing;70% for training and 30% for testing. Four image embedders including Vgg16, Vgg19, SqueezeNet, and Inception-v3 are used in the experiments. Experiment results showed that most of these models achieved promising accuracy, precision, recall, and F1-scores. KNN, ANN, and LR classifiers have achieved highest classification accuracies using SqueezeNet image embedder. © 2022 IEEE.

Developing Capabilities for Supply Chain Resilience in a Post-COVID World: A Machine Learning based Thematic Analysis

This study examines the past, present, and future of supply chain resilience (SCR) research in the context of COVID-19. Specifically, a total of 1,717 papers in the SCR field are classified into eleven thematic clusters, which are subsequently verified by a supervised machine learning approach. Each cluster is then analyzed within the context of COVID-19, leading to the identification of three associated capabilities (i.e., interconnectedness, transformability, and sharing) that firms should focus on to build a more resilient supply chain in the post-COVID world. The derived insights offer invaluable guidance not only for practicing managers, but also for scholars as they design their future research projects related to SCR for greatest impact. [ FROM AUTHOR]

Automatic Detection of Severely and Mildly Infected COVID-19 Patients with Supervised Machine Learning Models.

Objectives: When the prognosis of COVID-19 disease can be detected early, the intense-pressure and loss of workforce in health-services can be partially reduced. The primary-purpose of this article is to determine the feature-dataset consisting of the routine-blood-values (RBV) and demographic-data that affect the prognosis of COVID-19. Second, by applying the feature-dataset to the supervised machine-learning (ML) models, it is to identify severely and mildly infected COVID-19 patients at the time of admission. Material and methods: The sample of this study consists of severely (n = 192) and mildly (n = 4010) infected-patients hospitalized with the diagnosis of COVID-19 between March-September, 2021. The RBV-data measured at the time of admission and age-gender characteristics of these patients were analyzed retrospectively. For the selection of the features, the minimum-redundancy-maximum-relevance (MRMR) method, principal-components-analysis and forward-multiple-logistics-regression analyzes were used. The features set were statistically compared between mild and severe infected-patients. Then, the performances of various supervised-ML-models were compared in identifying severely and mildly infected-patients using the feature set. Results: In this study, 28 RBV-parameters and age-variable were found as the feature-dataset. The effect of features on the prognosis of the disease has been clinically proven. The ML-models with the highest overall-accuracy in identifying patient-groups were found respectively, as follows: local-weighted-learning (LWL)-97.86%, K-star (K*)-96.31%, Naive-Bayes (NB)-95.36% and k-nearest-neighbor (KNN)-94.05%. Also, the most successful models with the highest area-under-the-receiver-operating-characteristic-curve (AUC) values in identifying patient groups were found respectively, as follows: LWL-0.95%, K*-0.91%, NB-0.85% and KNN-0.75%. Conclusion: The findings in this article have significant a motivation for the healthcare professionals to detect at admission severely and mildly infected COVID-19 patients.

Anti-intellectualism amid the COVID-19 pandemic: The discursive elements and sources of anti-Fauci tweets.

Anti-intellectualism (resentment, hostility, and mistrust of experts) has become a growing concern during the pandemic. Using topic modeling and supervised machine learning, this study examines the elements and sources of anti-Fauci tweets as a case of anti-intellectual discourse on social media. Based on the theoretical framework of science-related populism, we identified three anti-intellectual discursive elements in anti-Fauci tweets: people-scientist antagonism, delegitimizing the motivation of scientists, and delegitimizing the knowledge of scientists. Delegitimizing the motivation of scientists appeared the most in anti-Fauci tweets. Politicians, conservative news media, and non-institutional actors (e.g. individuals and grassroots advocacy organizations) co-constructed the production and circulation of anti-intellectual discourses on Twitter. Anti-intellectual discourses resurged even under Twitter's content moderation mechanism. We discuss theoretical and practical implications for building public trust in scientists, effective science communication, and content moderation policies on social media.

Sentiment Analysis of Covid-19 Tweets by Supervised Machine Learning Models

The COVID-19 virus's transmissibility has sparked intense debate on social media sites, particularly Twitter. As a result, to employ resources efficiently and effectively, a comprehensive assessment of the situation is crucial. Therefore, COVID-19 tweet sentiment analysis is implemented in this research by employing a supervised machine learning (ML) approach. Data is retrieved from Twitter using the Tweepy API, pre-processed using pre-processing techniques, and sentiment extracted and labelled as positive or negative sentiments using the TextBlob library. Three separate feature extraction techniques are used: Bag-of-words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF) combination with 1-gram, and TF-IDF combination with 2-gram. The sentiment is then analyzed using ML classifiers such as Random Forest (RF) and Support Vector Machine (SVM). For clarity, the dataset is studied further using the deep learning method which is Long Short-Term Memory (LSTM) architecture. The four standard evaluation metrics, Receiver Operating Characteristic (ROC), and Area Under the Curve (AUC) were used to evaluate the performance of the models. The findings show that the RF classifier surpasses all other models with a 0.98 accuracy score when combining 2-gram TF-IDF features. In summary, the model may be used to categorize perspectives and will assist policymakers in making more educated decisions about how to respond to the current pandemic. © 2022, Success Culture Press. All rights reserved.

Detection of Antibodies for COVID-19 from Reflectance Spectrum Using Supervised Machine Learning

Since the coronavirus disease 2019 occurred, the lateral flow immunoassay (LFIA) test strip has become a global testing tool for convenience and low cost. However, some studies have shown that LFIA strips perform poorly compared to other professional testing methods. This paper proposes a new method to improve the accuracy of LFIA strips using spectral signals. A spectrochip module is applied to disperse the reflected light from the LFIA strips. The obtained spectral signals will be used for supervised machine learning. After training, the trained model has 93.8% accuracy compared to the standard test. This result indicated that the evaluation method based on the spectrum of LFIA strips could enhance the detection performance. © 2022 IEEE.