Machine Learning and Deep Learning based Stock Market Prediction considering Covid-19 as a Feature

India's capital markets are witnessing intense uncertainty due to global market failures. Since the outbreak of COVID-19, risk asset prices have plummeted sharply. Risk assets declined half or more compared to the losses in 2008 and 2009. The high volatility is likely to continue in the short term;as a result, the Indian markets have declined sharply. In this paper, we have used different algorithms such as Gated Recurrent Unit, Long Short-Term Memory, Support Vector Regressor, Decision Tree, Random Forest, Lasso Regression, Ridge Regression, Bayesian Ridge Regression, Gradient Boost, and Stochastic Gradient Descent Algorithm to predict financial markets based on historical data available along with economic and financial features during this pandemic. According to our findings, deep learning models can accurately estimate financial indexes by utilizing non-linear transaction data. We found that the Gated Recurrent Unit performs better than the existing model. © 2023 IEEE.

Decay rate estimation of respiratory viruses in aerosols and on surfaces under different environmental conditions.

Majority of the viral outbreaks are super-spreading events established within 2-10 h, dependent on a critical time interval for successful transmission between humans, which is governed by the decay rates of viruses. To evaluate the decay rates of respiratory viruses over a short span, we calculated their decay rate values for various surfaces and aerosols. We applied Bayesian regression and ridge regression and determined the best estimation for respiratory viruses, including severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), severe acute respiratory syndrome coronavirus (SARS-CoV), middle east respiratory syndrome coronavirus (MERS-CoV), influenza viruses, and respiratory syncytial virus (RSV); the decay rate values in aerosols for these viruses were 4.83 ± 5.70, 0.40 ± 0.24, 0.11 ± 0.04, 2.43 ± 5.94, and 1.00 ± 0.50 h-1, respectively. The highest decay rate values for each virus type differed according to the surface type. According to the model performance criteria, the Bayesian regression model was better for SARS-CoV-2 and influenza viruses, whereas ridge regression was better for SARS-CoV and MERS-CoV. A simulation using a better estimation will help us find effective non-pharmaceutical interventions to control virus transmissions.

Effect of geographical factors on reference values of creatine kinase isoenzyme.

The aim of this study was to investigate the geographical spatial distribution of creatine kinase isoenzyme (CK-MB) in order to provide a scientific basis for clinical examination. The reference values of CK-MB of 8697 healthy adults in 137 cities in China were collected by reading a large number of literates. Moran index was used to determine the spatial relationship, and 24 factors were selected, which belonged to terrain, climate, and soil indexes. Correlation analysis was conducted between CK-MB and geographical factors to determine significance, and 9 significance factors were extracted. Based on R language to evaluate the degree of multicollinearity of the model, CK-MB Ridge model, Lasso model, and PCA model were established, through calculating the relative error to choose the best model PCA, testing the normality of the predicted values, and choosing the disjunctive kriging interpolation to make the geographical distribution. The results show that CK-MB reference values of healthy adults were generally correlated with latitude, annual sunshine duration, annual mean relative humidity, annual precipitation amount, and annual range of air temperature and significantly correlated with annual mean air temperature, topsoil gravel content, topsoil cation exchange capacity in clay, and topsoil cation exchange capacity in silt. The geospatial distribution map shows that on the whole, it is higher in the north and lower in the south, and gradually increases from the southeast coastal area to the northwest inland area. If the geographical factors are obtained in a location, the CK-MB model can be used to predict the CK-MB of healthy adults in the region, which provides a reference for us to consider regional differences in clinical diagnosis.

Computed Tomography Simulator (Ctlab)

University of Oulu and Oulu University of Applied Sciences have established a unique medical imaging teaching and testing laboratory in collaboration with Oulu University Hospital in a European Regional Development Fund -project. Virtually implemented medical imaging devices (CT, MRI, radiography) are unique features of the lab. Many of the virtual tools have been developed by the universities themselves. One of the virtual tools implemented during the project is the CTlab simulator, which can be widely used in computed tomography training for all professionals who use radiation in their work. The CTlab provides fast, comprehensive, and efficient solutions for numerical CT simulations with low hardware requirements. The simulator has been developed to introduce the basic operations and workflow behind the CT imaging modality and to illustrate how the polychromatic x-ray spectrum, various imaging parameters, scan geometry and CT reconstruction algorithm affect the quality of the detected images. Key user groups for the simulator include medical physics, engineering, and radiographer students. CTlab has been created with MATLAB's app designer feature. It offers its user the opportunity to select the virtual imaging target, to adjust CT imaging parameters (image volume, scan angles, detector element size and detector width, noise, algorithm/geometry specific parameters), to select specific scan geometry, to observe projection data from selected imaging target with polychromatic x-ray spectrum, and to select the specific algorithm for image reconstruction (FBP, least squares, Tikhonov regularization). The CTlab has so far been used at a postgraduate course on computed tomography technology with encouraging feedback from the students. At the course, teaching of CT modality were performed by using the simulator, giving students unlimited opportunity to practice the use of virtual imaging device and participate demonstrations remotely during the Covid-19 pandemic. Using CTlab in teaching enhances and deepens the learning experience in the physics behind computed tomography. CTlab can be used remotely (https://www.oulu.fi/fi/projektit/laaketieteellisen-kuvantamisen-opetus-ja-testilaboratorio-0), which makes teaching and training of CT scanner usage successful regardless of time and place. The simulator enables more illustrative and in-depth teaching and offers cost-effectiveness, versatility, and flexibility in education. CTlab can also be used to support teaching in special situations, such as during the Covid-19 pandemic when simulator is utilized remotely to perform teaching-related demonstrations flexibly and safely.Copyright © 2023 Southern Society for Clinical Investigation.

A new ridge estimator for linear regression model with some challenging behavior of error term

Ridge regression is a variant of linear regression that aims to circumvent the issue of collinearity among predictors. The ridge parameter (Formula presented.) has an important role in the bias-variance tradeoff. In this article, we introduce a new approach to select the ridge parameter to deal with the multicollinearity problem with different behavior of the error term. The proposed ridge estimator is a function of the number of predictors and the standard error of the regression model. An extensive simulation study is conducted to assess the performance of the estimators for the linear regression model with different error terms, which include normally distributed, non-normal and heteroscedastic or autocorrelated errors. Based upon the criterion of mean square error (MSE), it is found that the new proposed estimator outperforms OLS, commonly used and closely related estimators. Further, the application of the proposed estimator is provided on the COVID-19 data of India. © 2023 Taylor & Francis Group, LLC.

Case-Control Study on the Routes of Transmission of SARS-CoV-2 after the Third Pandemic Wave in Tuscany, Central Italy.

The emergence of hyper-transmissible SARS-CoV-2 variants that rapidly became prevalent throughout the world in 2022 made it clear that extensive vaccination campaigns cannot represent the sole measure to stop COVID-19. However, the effectiveness of control and mitigation strategies, such as the closure of non-essential businesses and services, is debated. To assess the individual behaviours mostly associated with SARS-CoV-2 infection, a questionnaire-based case-control study was carried out in Tuscany, Central Italy, from May to October 2021. At the testing sites, individuals were invited to answer an online questionnaire after being notified regarding the test result. The questionnaire collected information about test result, general characteristics of the respondents, and behaviours and places attended in the week prior to the test/symptoms onset. We analysed 440 questionnaires. Behavioural differences between positive and negative subjects were assessed through logistic regression models, adjusting for a fixed set of confounders. A ridge regression model was also specified. Attending nightclubs, open-air bars or restaurants and crowded clubs, outdoor sporting events, crowded public transportation, and working in healthcare were associated with an increased infection risk. A negative association with infection, besides face mask use, was observed for attending open-air shows and sporting events in indoor spaces, visiting and hosting friends, attending courses in indoor spaces, performing sport activities (both indoor and outdoor), attending private parties, religious ceremonies, libraries, and indoor restaurants. These results might suggest that during the study period people maintained a particularly responsible and prudent approach when engaging in everyday activities to avoid spreading the virus.

Similarity-Principle-Based Machine Learning Method for Clinical Trials and Beyond

With recent success in supervised learning, artificial intelligence (AI) and machine learning (ML) can play a vital role in precision medicine. Deep learning neural networks have been used in drug discovery when larger data is available. However, applications of machine learning in clinical trials with small sample size (around a few hundreds) are limited. We propose a Similarity-Principle-Based Machine Learning (SBML) method, which is applicable for small and large sample size problems. In SBML, the attribute-scaling factors are introduced to objectively determine the relative importance of each attribute (predictor). The gradient method is used in learning (training), that is, updating the attribute-scaling factors. We evaluate SBML when the sample size is small and investigate the effects of tuning parameters. Simulations show that SBML achieves better predictions in terms of mean squared errors for various complicated nonlinear situations than full linear models, optimal and ridge regressions, mixed effect models, support vector machine and decision tree methods. Copyright © 2022 American Statistical Association.

Estimating COVID-19 Cases Using Machine Learning Regression Algorithms

Background: Coronavirus refers to a large group of RNA viruses that infects the respira-tory tract in humans and also causes diseases in birds and mammals. SARS-CoV-2 gives rise to the infectious disease “COVID-19”. In March 2020, coronavirus was declared a pandemic by the WHO. The transmission rate of COVID-19 has been increasing rapidly;thus, it becomes indispensable to estimate the number of confirmed infected cases in the future. Objective: The study aims to forecast coronavirus cases using three ML algorithms, viz., support vector regression (SVR), polynomial regression (PR), and Bayesian ridge regression (BRR). Methods: There are several ML algorithms like decision tree, K-nearest neighbor algorithm, Ran-dom forest, neural networks, and Naïve Bayes, but we have chosen PR, SVR, and BRR as they have many advantages in comparison to other algorithms. SVM is a widely used supervised ML algorithm developed by Vapnik and Cortes in 1990. It is used for both classification and regression. PR is known as a particular case of Multiple Linear Regression in Machine Learning. It models the rela-tionship between an independent and dependent variable as nth degree polynomial. Results: In this study, we have predicted the number of infected confirmed cases using three ML algorithms, viz. SVR, PR, and BRR. We have assumed that there are no precautionary measures in place. Conclusion: In this paper, predictions are made for the upcoming number of infected confirmed cases by analyzing datasets containing information about the day-wise past confirmed cases using ML models (SVR, PR and BRR). According to this paper, as compared to SVR and PR, BRR performed far better in the future forecasting of the infected confirmed cases owing to coronavirus. © 2022 Bentham Science Publishers.

Comparative analysis of time series prediction model for forecasting COVID-19 trend

The outbreak of the COVID-19 pandemic occurred some time ago, making the world a pandemic. Based on this condition is important to predict early to prevent the COVID-19 disease if someday pandemic occurs. The aim of the study is to compare the analysis result of cumulative cases of COVID-19 using multiple linear regression (MLR), ridge regression (RR), and long short term memory (LSTM) models for cases study Java and Bali islands. We chose both islands as a case study because they have very dense populations. These three models are the most widely used time series-based prediction models and have relatively high accuracy values. The predictive variables used are the number of cumulative cases, the daily cases, and population density. The research data was taken from Kaggle and processed using google collabs. Data was taken from January 20, 2020, to August 8, 2020, and data training was carried out for 12 days. The results show the accuracy of LSTM is better than other models. it can be seen in the accuracy value (99.8%) of the model test result. The testing model uses R2, mean square error (MSE), and root mean square error (RMSE). © 2022 Institute of Advanced Engineering and Science. All rights reserved.

Correlations between the urban built environmental factors and the spatial distribution at the community level in the reported COVID-19 samples: A case study of Wuhan.

COVID-19 has dramatically changed the lifestyle of people, especially in urban environments. This paper investigated the variations of built environments that were measurably associated with the spread of COVID-19 in 150 Wuhan communities. The incidence rate in each community before and after the lockdown (January 23, 2020), as respective dependent variables, represented the situation under normal circumstances and non-pharmaceutical interventions (NPI). After controlling the population density, floor area ratio (FAR), property age and sociodemographic factors, the built environmental factors in two spatial dimensions, the 15-minute walking life circle and the 10-minute cycling life circle, were brought into the Hierarchical Linear Regression Model and the Ridge Regression Model. The results indicated that before lockdown, the number of markets and schools were positively associated with the incidence rate, while community population density and FAR were negatively associated with COVID-19 transmission. After lockdown, FAR, GDP, the number of hospitals (in the 15-minute walking life circle) and the bus stations (in the 10-minute cycling life circle) became negatively correlated with the incidence rate, while markets remained positive. This study effectively extends the discussions on the association between the urban built environment and the spread of COVID-19. Meanwhile, given the limitations of sociodemographic data sources, the conclusions of this study should be interpreted and applied with caution.

The Model of Regularization Coefficient in Polynomial Regression for Modelling the Spread of COVID-19 in Romania

Research on the pandemic situation of COVID-19 is very important for delivering detailed risk analyzes based on estimating the peak of the pandemic. The machine learning approach has a major role to play in predicting the number of COVID-19 cases. Most research on COVID-19 uses polynomial regression for analysis. When a regression model is build, often, the model fails to generalize on unseen data. For instance, the model might end up becoming too complex, having significantly high variance due to over-fitting, thereby impacting the model performance on new data sets. To avoid over-fitting of the polynomial regression, a regularization method can be used to suppress the coefficients of the higher order polynomial, a principle that allows the smoothness of the regression function. The aim of this paper is to formulate a mathematical model for regularization coefficient in polynomial regression and evaluate this approach to enable obtaining meaningful results on a COVID-19 data set. Therefore we believe that our results will contribute to a better understanding of the over-fitting process in polynomial regression. Our methodology consists of following major steps: i) optimizing the model using k-fold cross-validation for finding an optimal regularization coefficient and ii) comparing the performance of ridge regression and lasso regression using accuracy metrics. Moreover, our approach could also have a potential impact in machine learning education, regarding the understanding of the underlying mathematical machinery behind polynomial regression algorithms. The obtained results show that the polynomial model built using lasso regression, outperforms the ridge regression. © 2022 IEEE.

End-to-End Encryption and Prediction of Medical Insurance Cost

Health-care costs are rising on a daily basis after the advent of Covid. Most importantly, health issues are becoming more prevalent and critical. As a result, predicting medical insurance cost has become unavoidable as many people choose insurance. However, for a secure system, the entire prediction model for each customer should be encrypted end-to-end. To create a better prediction model, Machine learning regression algorithms are used. The prediction model will be encrypted end-to-end. This paper will give the steps of developing a reliable medical insurance cost prediction model. © 2022 IEEE.

ON COVID-19 EPIDEMIC PROCESS SIMULATION: THREE REGRESSION APPROACHES INVESTIGATIONS

An outbreak of a new coronavirus infection was first recorded in Wuhan, China, in December 2019. On January 30, 2020, the World Health Organization declared the outbreak a Public Health Emergency of International Concern and on March 11, it a pandemic. As of January 2022, over 340 million cases have been reported worldwide;more than 5.5 million deaths have been confirmed, making the COVID-19 pandemic one of the deadliest in history. The digitalization of all spheres of society makes it possible to use mathematical and simulation modeling to study the development of the virus. Building adequate models of the epidemic process will make it possible not only to predict its dynamics but also to conduct experimental studies to identify factors affecting the development of a pandemic, determine the behavior of the virus in certain areas, assess the effectiveness of measures aimed at stopping the spread of infection, as well as assess the resources needed to counter the epidemic growth of the disease. This study aims to develop three regression models of the COVID-19 epidemic process in given territories and to investigate the experimental results of the simulation. The research is targeted at the COVID-19 epidemic process. The research subjects are methods and models of epidemic process simulation, which include machine learning methods, particularly linear regression, Ridge regression, and Lasso regression. To achieve the research aim, we have used forecasting methods and have built the COVID-19 epidemic process and regression models. As a result of experiments with the developed model, the predictive dynamics of the epidemic process of COVID-19 in Ukraine, Germany, Japan, and South Korea for 3, 7, 10, 14, 21, and 30 days were obtained. The authorities making decisions on the implementation of anti-epidemic measures can use such predictions to solve the problems of operational analysis of the epidemic situation, an analysis of the effectiveness of already implemented anti-epidemic measures, medium-term planning of resources needed to combat the pandemic, etc. Conclusions. This paper describes experimental research on implementing three regression models of the COVID-19 epidemic process. These are models of linear regression, Ridge regression, and Lasso regression. COVID-19 daily new cases statistics were verified by these models for Ukraine, Germany, Japan, and South Korea, provided by the Johns Hopkins Coronavirus Resource Center. All built models have sufficient accuracy to make decisions on the implementation of anti-epidemic measures to combat the COVID-19 pandemic in the selected area. Depending on the forecast period, regression models can be used to solve different Public Health tasks. © 2022. Dmytro Chumachenko, Ievgen Meniailov, Kseniia Bazilevych, Olha Chub. All Rights Reserved.

The prediction of coronavirus disease 2019 outbreak on Bangladesh perspective using machine learning: a comparative study

Coronavirus disease 2019 (COVID-19) has made a huge pandemic situation in many countries of the world including Bangladesh. If the increase rate of this threat can be forecasted, immediate measures can be taken. This study is an effort to forecast the threat of present pandemic situation using machine learning (ML) forecasting models. Forecasting was done in three categories in the next 30 days range. In our study, multiple linear regression performed best among the other algorithms in all categories with R2 score of 99% for first two categories and 94% for the third category. Ridge regression performed great for the first two categories with R2 scores of 99% each but performed poorly for the third category with R2 score of 43%. Lasso regression performed reasonably well with R2 scores of 97%, 99% and 75% for the three categories. We also used Facebook Prophet to predict 30 days beyond our train data which gave us healthy R2 scores of 92% and 83% for the first two categories but performed poorly for the third category with R2 score of 34%. Also, all the models’ performances were evaluated with a 40-day prediction interval in which multiple linear regression outperformed other algorithms. © 2022 Institute of Advanced Engineering and Science. All rights reserved.

PREDICTION OF DEMAND FOR RED BLOOD CELLS USING RIDGE REGRESSION, ARTIFICIAL NEURAL NETWORK, AND INTEGRATED TAGUCHI-ARTIFICIAL NEURAL NETWORK APPROACH

Regional blood centers collect donated blood and distribute processed blood to the blood transfusion centers according to their need. The prediction of blood components to be demanded by transfusion centers becomes more important, especially these days when the impact of COVID-19 is increasing. Since donors are afraid to go to blood donation centers, blood component stocks rapidly decrease. This study aims to predict the blood transfusion centers' demand for quantities of red blood cells, which is an important blood component, from a regional blood center by using the artificial neural network method. The method's parameters values affect the prediction performance of the method. Therefore, the Taguchi method is integrated with artificial neural network methods to optimize the parameters. The prediction results of the integrated Taguchi-artificial neural network approach, artificial neural network method, and ridge regression method are each compared with the actual demand of regional blood centers. It is determined that the integrated Taguchi-artificial neural network approach predicts actual demand more accurately.

Predicting the Total number of COVID-19 Deaths by County for the State of Florida: Ridge Regression Approach

Coronavirus disease 2019 (COVID-19) is a novel infectious disease that was detected in Wuhan, China at the end of 2019. The virus quickly spread worldwide and caused a global pandemic. This paper investigates if there are any regressors that could help impact the number of deaths due to COVID-19. The variables that were used in the models were total deaths, hospitalizations, total cases, population, minimum temperature, average temperature, maximum temperature, precipitation, mobility index, median age, adults age 65 or older, PM2.5 average, ozone average, and positive non-residents. After fitting six different regression models, we found that the most significant regressors were hospitalizations per county, total cases per county, population per county, median age per county, positive adults 65 or older per county, and positive non-residents per county. The COVID-19 data of this paper will be an excellent source for illustrating the multicollinear linear regression models. © 2021, World Scientific and Engineering Academy and Society. All rights reserved.

Estimate the Housing Price under the Impact of COVID-19 and Possible Migration Due to the Demand for Density

Different population among the states shows a heterogeneous housing price trend during the past years. Any possible abnormal migration will cause price change. Thus, the migration could be tackled by comparing the current price trend with the data in past 10 years. COVID-19 is a strong effect which could cause migration. In order to observe the possible migration under this situation, wo high-population states were chosen as examples - California and New York, to compare with two low-population states - Nevada and Ohio. Three machine learning techniques have been used (Random Forest, XGboost, and Ridge and Lasso regression) to forecast housing price in U.S.: the difference between the real price and forecast price trend will show the amount of real estate transactions affect by the pandemic. The observed data was compared with the predicted results after COVID-19. The final result didn't show a strong evidence that would verify a possible migration, but the answer will be clearer with further studies. © 2021 IEEE.

Factors Influencing High-Rise Gated Community Collective Action Effectiveness: Conceptualization of the Social-Ecological System (SES) Framework

Managing common property in gated communities is challenging. Although numerous studies have demonstrated that there are several determinants of collective action effectiveness and performances in gated communities, empirical research drawing on a multidimensional social-ecological system (SES) framework in quantitatively exploring relationships between institutional–physical–social factors and gated community collective action remains lacking. Therefore, based on Ostrom’s social-ecological system (SES) framework, this study attempts to identify factors influencing the self-organizing system (collective action) of gated communities in China. Using stratified purposive sampling, ten gated communities with various characteristics in the Taigu district were selected, in which questionnaires were then distributed to 414 households to collect valid data within the communities. Taking the ridge regression as a more robust predictive SES model with a penalty value of k = 0.1 and regularization, R Square of 0.882, this study, among 14 factors, ultimately identified six key institutional–social–ecological factors based on the descending standardized effect size, and they are: (i) types of community;(ii) presence of leaders;(iii) exclusiveness systems of a gated community;(iv) age of gated community;(v) strict enforcement of rules;and (vi) number of households that affect residents’ collective action in terms of community security, hygiene and cleanliness, and facility quality. The research findings provide urban managers and communities novel insights to formulate strategic policies towards sustainable housing and building management.

Regression Analysis and Prediction of the COVID-19

The corona virus disease is recognized as a global threat to the health industry and is a new challenge to the research area. To deal with this corona virus disease (COVID-19), which is currently sparked, all over the globe, machine learning (ML) plays a major role in variety of ways. This paper presents the analysis of the deadly COVID-19 outbreak to fight against this pandemic. This study is based on the dataset of confirmed cases, deaths, and recoveries worldwide as provided by the Johns Hopkins University. At first, we analyzed the pattern and characteristics of the growth of the pandemic by publicly available data. Secondly, we presented a comparative study and, finally, developed a future forecast model by taking three machine learning algorithms are support vector machine, linear regression, and Bayesian ridge regression. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Covid-19 Dashboard: Supervised learning ML model based Covid-19 prediction analysis and identifying early-stage symptoms

Following Standard Operating Procedures and being Social distanced is now the new norm for most of the people worldwide, amidst this pandemic. At this crucial time, people must be updated regarding, virus hotspots, containment zones and more associated information. The recent outbreak has taken the world by surprise, forcing lockdowns in most of the countries and affecting the public health systems. In response to the outbreak, Governments of many countries have shown interest in contact tracing applications. The main goal of developing the application is to provide all the information related to COVID-19 or any pandemic situation to the citizen of the country. The project holds plenty of relevance in today's time when people are finding solutions to protect themselves from the pandemic. Our project is an proposal to confirm the utmost safety for the citizens of our country from the deadly coronavirus disease. In quintessence, it connects the health services of the country to its citizens at this unstable time. It can assist a person to follow adequate measures to avoid infection. Application users are also able to understand if they are currently being exploited to covid-19 related symptoms. The responsiveness of the mobile platform makes it easy for the users to perform self-diagnosis and inform whether there is a need to consult a doctor. © 2021 IEEE.