Machine learning-based diffusion model for prediction of coronavirus-19 outbreak.

The coronavirus pandemic has been globally impacting the health and prosperity of people. A persistent increase in the number of positive cases has boost the stress among governments across the globe. There is a need of approach which gives more accurate predictions of outbreak. This paper presents a novel approach called diffusion prediction model for prediction of number of coronavirus cases in four countries: India, France, China and Nepal. Diffusion prediction model works on the diffusion process of the human contact. Model considers two forms of spread: when the spread takes time after infecting one person and when the spread is immediate after infecting one person. It makes the proposed model different over other state-of-the art models. It is giving more accurate results than other state-of-the art models. The proposed diffusion prediction model forecasts the number of new cases expected to occur in next 4 weeks. The model has predicted the number of confirmed cases, recovered cases, deaths and active cases. The model can facilitate government to be well prepared for any abrupt rise in this pandemic. The performance is evaluated in terms of accuracy and error rate and compared with the prediction results of support vector machine, logistic regression model and convolution neural network. The results prove the efficiency of the proposed model.

Can COVID-19 deaths and confirmed cases predict the uncertainty indexes? A multiscale analysis

Purpose: This study aims to examine the multiscale predictability power of COVID-19 deaths and confirmed cases on the S&P 500 index (USA), CAC30 index (France), BSE index (India), two strategic commodity futures (West Texas intermediate [WTI] crude oil and Gold) and five main uncertainty indices Equity Market Volatility Ticker (EMV), CBOE Volatility Index (VIX), US Economic Policy Uncertainty (EPU), CBOE Crude Oil Volatility Index (OVX) and CBOE ETF Gold Volatility Index (GVZ). Furthermore, the authors analyze the impact of uncertainty indices and COVID-19 deaths and confirmed cases on the price returns of stocks (S&P500, CAC300 and BSE), crude oil and gold. Design/methodology/approach: The authors used the wavelet coherency method and quantile regression approach to achieve the objectives. Findings: The results show strong multiscale comovements between the variables under investigation. Lead-lag relationships vary across frequencies. Finally, COVID-19 news is a powerful predictor of the uncertainty indices at intermediate (4–16 days) and low (32–64 days) frequencies for EPU and at low frequency for EMV, VIX, OVX and GVZ indices from January to April 2020. The S&P500, CAC30 and BSE indexes and gold prices comove with COVID-19 news at low frequencies during the sample period. By contrast, COVID-19 news and WTI oil moderately correlated at low frequencies. Finally, the returns on equity and commodity assets are influenced by uncertainty indices and are sensitive to market conditions. Originality/value: This study contributes to the literature by exploring the time and frequency dependence between COVID-19 news (confirmed and death cases) on the returns of financial and commodity markets and uncertainty indexes. The findings can assist market participants and policymakers in considering the predictability of future prices and uncertainty over time and across frequencies when setting up regulations that aim to enhance market efficiency. © 2023, Emerald Publishing Limited.

STG-Net: A COVID-19 prediction network based on multivariate spatio-temporal information.

The modern urban population features a high population density and a fast population flow, and COVID-19 has strong transmission ability, long incubation period, and other characteristics. Considering only the time sequence of COVID-19 transmission cannot effectively respond to the current epidemic transmission situation. The distance between cities and population density information also have a significant impact on the transmission of the virus. Currently, cross-domain transmission prediction models do not fully exploit the time-space information and fluctuation trend of data, and cannot reasonably predict the trend of infectious diseases by integrating time-space multi-source information. To solve this problem, this paper proposes the COVID-19 prediction network (STG-Net) based on multivariate spatio-temporal information, which introduces the Spatial Information Mining module (SIM) and the Temporal Information Mining module (TIM) to mine the spatio-temporal information of the data in a deeper level, and uses the slope feature method to further mine the fluctuation trend of the data. Also, we introduce the Gramian Angular Field module (GAF), which converts one-dimensional data into two-dimensional images, further enhancing the network's feature mining capability in the time and feature dimension, ultimately combining spatiotemporal information to predict daily newly confirmed cases. We tested the network on datasets from China, Australia, the United Kingdom, France, and Netherlands. The experimental results show that STG-Net has better prediction performance than existing prediction models, with an average decision coefficient R2 of 98.23% on the datasets from five countries, as well as good long- and short-term prediction ability and overall good robustness.

Chaos of COVID-19 Superspreading Events: An Analysis Via a Data-driven Approach

Superspreading has become a key mechanism of COVID-19 transmission which creates chaos. The classical approach of compartmental models may not sufficiently reflect the epidemiological situation amid superspreading events (SSEs). We perform a data-driven approach and recognise the deterministic chaos of confirmed cases. The first derivative (≈difference of total confirmed cases) and the second derivative (≈difference of the first derivative) are used upon SSEs to showcase the chaos. Varying solution trajectories, sensitivity and numerical unpredictability are the chaotic characteristics discussed here. © 2023 Indian Institute of Health Management Research.

The role of the mass vaccination programme in combating the COVID-19 pandemic: An LSTM-based analysis of COVID-19 confirmed cases.

The COVID-19 virus has impacted all facets of our lives. As a global response to this threat, vaccination programmes have been initiated and administered in numerous nations. The question remains, however, as to whether mass vaccination programmes result in a decrease in the number of confirmed COVID-19 cases. In this study, we aim to predict the future number of COVID-19 confirmed cases for the top ten countries with the highest number of vaccinations in the world. A well-known Deep Learning method for time series analysis, namely, the Long Short-Term Memory (LSTM) networks, is applied as the prediction method. Using three evaluation metrics, i.e., Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), we found that the model built by using LSTM networks could give a good prediction of the future number and trend of COVID-19 confirmed cases in the considered countries. Two different scenarios are employed, namely: 'All Time', which includes all historical data; and 'Before Vaccination', which excludes data collected after the mass vaccination programme began. The average MAPE scores for the 'All Time' and 'Before Vaccination' scenarios are 5.977% and 10.388%, respectively. Overall, the results show that the mass vaccination programme has a positive impact on decreasing and controlling the spread of the COVID-19 disease in those countries, as evidenced by decreasing future trends after the programme was implemented.

Dynamic variations in COVID-19 with the SARS-CoV-2 Omicron variant in Kazakhstan and Pakistan.

BACKGROUND: The ongoing coronavirus disease 2019 (COVID-19) pandemic caused by the severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) and the Omicron variant presents a formidable challenge for control and prevention worldwide, especially for low- and middle-income countries (LMICs). Hence, taking Kazakhstan and Pakistan as examples, this study aims to explore COVID-19 transmission with the Omicron variant at different contact, quarantine and test rates. METHODS: A disease dynamic model was applied, the population was segmented, and three time stages for Omicron transmission were established: the initial outbreak, a period of stabilization, and a second outbreak. The impact of population contact, quarantine and testing on the disease are analyzed in five scenarios to analysis their impacts on the disease. Four statistical metrics are employed to quantify the model's performance, including the correlation coefficient (CC), normalized absolute error, normalized root mean square error and distance between indices of simulation and observation (DISO). RESULTS: Our model has high performance in simulating COVID-19 transmission in Kazakhstan and Pakistan with high CC values greater than 0.9 and DISO values less than 0.5. Compared with the present measures (baseline), decreasing (increasing) the contact rates or increasing (decreasing) the quarantined rates can reduce (increase) the peak values of daily new cases and forward (delay) the peak value times (decreasing 842 and forward 2 days for Kazakhstan). The impact of the test rates on the disease are weak. When the start time of stage II is 6 days, the daily new cases are more than 8 and 5 times the rate for Kazakhstan and Pakistan, respectively (29,573 vs. 3259; 7398 vs. 1108). The impact of the start times of stage III on the disease are contradictory to those of stage II. CONCLUSIONS: For the two LMICs, Kazakhstan and Pakistan, stronger control and prevention measures can be more effective in combating COVID-19. Therefore, to reduce Omicron transmission, strict management of population movement should be employed. Moreover, the timely application of these strategies also plays a key role in disease control.

Association Rules Extraction From the Coronavirus Disease 2019: Attributes on Morbidity and Mortality

This research was aimed to extract association rules on the morbidity and mortality of corona virus disease 2019 (COVID-19). The dataset has four attributes that determine morbidity and mortality;including Confirmed Cases, New Cases, Deaths, and New Deaths. The dataset was obtained as of 2nd April, 2020 from the WHO website and converted to transaction format. The Apriori algorithm was then deployed to extract association rules on these attributes. Six rules were extracted: Rule 1. {Deaths, NewDeaths}=>{NewCases}, Rule 2. {ConfCases, NewDeaths}=>{NewCases}, Rule 3. {ConfCases, Deaths}=>{NewCases}, Rule 4. {Deaths, NewCases}=>{NewDeaths}, Rule 5. {ConfCases, Deaths}=>{NewDeaths}, Rule 6. {ConfCases, NewCases}=>{NewDeaths}, with confidence 0.96, 0.96, 0.86, 0.66, 0.59, 0.51 respectively. These rules provide useful information that is vital on how to curtail further spread and deaths from the virus, both in areas where the pandemic is already ravaging and in areas yet to experience the outbreak.

Impact of containment measures on community mobility, daily confirmed cases, and mortality in the third wave of COVID-19 epidemic in Myanmar.

In Myanmar, third wave of COVID-19 epidemic began with a surge of confirmed cases in the last week of May 2021. The laboratory-confirmed cases and deaths distinctly increased within 9 weeks. The government and the Ministry of Health adopted containment measures to flatten the peak of the epidemic and to suppress the disease transmission. The strictly containment measures: stay-at-home restrictions, school closure, and office closure have reduced the community mobility, confirmed cases and mortality. Therefore, the timely containment measures implemented by the government were important to reduce the transmission as observed in the third wave of COVID-19 epidemic in Myanmar.

Trends in managing COVID-19 from an emerging infectious disease to a common respiratory infectious disease: What are the subsequent impacts on and new challenges for healthcare systems?

Targeting the 9 countries with the highest cumulative number of newly confirmed cases in the past year, we analyzed the case fatality ratio (CFR) among newly confirmed cases and the vaccination rate (two or more doses of vaccine per 100 people) in the United States of America (USA), India, France, Germany, Brazil, the Republic of Korea, Japan, Italy, and the United Kingdom (UK) for the period of 2020-2022. Data reveal a decrease in the CFR among newly confirmed cases since the beginning of 2022, when transmission of the Omicron variant predominates, and an increase in vaccination rates. The Republic of Korea had the lowest CFR among newly confirmed cases (0.093%) in 2022 and the highest vaccination rate (86.27%). Japan had the second highest vaccination rate (83.12%) and a decrease in the CFR among newly confirmed cases of 1.478% in 2020, 1.000% in 2021, and 0.148% in 2022; while the average estimated fatality ratio for seasonal influenza from 2015-2020 was 0.020%. Currently, most countries are now easing COVID-19-related restrictions and are exploring a shift in management of COVID-19 from an emerging infectious disease to a common respiratory infectious disease that can be treated as the equivalent of seasonal or regional influenza. However, compared to influenza, infection with the Omicron variant still has a higher fatality ratio, is more transmissible, and the size of future outbreaks cannot be accurately predicted due to the uncertainty of viral mutation. More importantly, as countries shift their response strategies to COVID-19, there is an urgent need at this time to clarify what the subsequent impacts on healthcare systems and new challenges will be, including the clinical response, the dissemination of scientific information, vaccination campaigns, the creation of future surveillance and response systems, the cost of treatments and vaccinations, and the flexible use of big data in healthcare systems.

COVID-19 pandemic: environmental and social factors influencing the spread of SARS-CoV-2 in São Paulo, Brazil.

The new coronavirus SARS-CoV-2 has infected more than 14 million people worldwide so far. Brazil is currently the second leading country in number of cases of COVID-19, while São Paulo state accounts for 20% of total confirmed cases in Brazil. The aim of this study was to assess environmental and social factors influencing the spread of SARS-CoV-2 in the expanded metropolitan area of São Paulo, Brazil. Firstly, a spatial analysis was conducted to provide insights into the spread of COVID-19 within the expanded metropolitan area. Moreover, Spearman correlation test and sensitivity analysis were performed to assess social indicators and environmental conditions which possibly influence the incidence of COVID-19. Our results reveal that the spread of COVID-19 from the capital city São Paulo-its epicenter in Brazil-is directly associated with the availability of highways within the expanded metropolitan area of São Paulo. As for social aspects, COVID-19 infection rate was found to be both positively correlated with population density, and negatively correlated with social isolation rate, hence indicating that social distancing has been effective in reducing the COVID-19 transmission. Finally, COVID-19 infection rate was found to be inversely correlated with both temperature and UV radiation. Together with recent literature our study suggests that the UV radiation provided by sunlight might contribute to depletion of SARS-CoV-2 infectivity.

Effect of the Universal Health Coverage Healthcare System on Stock Returns During COVID-19: Evidence From Global Stock Indices.

The increased uncertainty caused by a sudden epidemic disease has had an impact on the global financial market. We aimed to assess the primary healthcare system of universal health coverage (UHC) during the coronavirus disease (COVID-19) pandemic and its relationship with the financial market. To this end, we employed the abnormal returns of 68 countries from January 2, 2019, to December 31, 2020, to test the impact of the COVID-19 outbreak on abnormal returns in the stock market and determine how a country's UHC changes the impact of a sudden pandemic on abnormal returns. Our findings show that the sudden onset of an epidemic disease results in unevenly distributed medical system resources, consequently diminishing the impact of UHC on abnormal returns.

Statistical investigation on association between the cumulative number of fully vaccinated people in the U.S. and the daily Covid-19 confirmation cases

Background: limited research about Covid-19 has been done on investigating the relationship between the number of vaccinated people and confirmed cases. We investigate the hypothesis, that the number of confirmed cases would negatively correlate with the number of people fully vaccinated. Methods: The data we chose to analyze is the number of Covid-19 confirmed cases versus the cumulative number of vaccinated people in the U.S. The data is collected from CDC's official website. The data was updated daily from 13 December 2020 (The start date when the Covid-19 vaccine was first available in the U.S.) till the date we collected it, 16 June 2021. Conclusion: our study indicates that the number of Covid-19 confirmed cases decreases as the number of fully vaccinated people increases. The results of this study will provide reasonable suggestions to people who are currently uncertain about the safety and effectiveness of the vaccines and convey profound cosmopolitan implications on other countries to contain the Covid-19 outbreak. © COPYRIGHT SPIE.

COVID-19 and Survival Strategies of Small Businesses in Nigeria

Introduction: The study examined the effect of COVID-19 on the survival strategies of small businesses in Nigeria. Materials and method: The applied survey research design with a close ended questionnaire which was administered to the respondents who were the owners of small businesses in Benue State of Nigeria. The variables used were number of deaths, number of confirmed cases and number of recovery cases which were used as measures of COVID-19 while survival strategies were measured with retrenchment strategies, investment strategies and ambidextrous strategies. The population of the study is the entire small businesses in Benue State of Nigeria and the sample size of 297 was derived using Taro Yamane formula. The variables were tested for reliability and result showed that all the variables were reliable. The study used regression with the aid of SPSS version 20. Results: There was a negative and significant effect of COVID-19 on survival strategies of small businesses in Benue State of Nigeria. Conclusion: The study recommended that small businesses in Benue State should continue to apply survival strategies during COVID-19 such as retrenchment strategies in terms reduction in the number of employments, reduction in expenditure (additional cost or overhead cost) and closure of additional branches of business establishment. They should also continue to adopt investment strategies such as investment in innovation, increase in resources and estimating growth measures of the firms.

The study of the effect of the data collected during vaccination period on the prediction of the number of Covid-19 cases

Coronavirus disease (Covid-19) is a serious health problem for the world. Most of the countries are affected by this infectious disease. Many countries have started vaccination against Covid-19. The number of confirmed cases every day changes rapidly. Public health planners want to know these numbers in advance to arrange health facilities accordingly. Many machine learning models have been developed for the prediction of the number of Covid-infected people. The accuracy of these models depends upon the training data. Data collected during the period when there is no vaccination and data collected during the vaccination period have different properties. The models trained on different datasets perform differently. In this paper, we study the effect of the data collected during the vaccination period. The study will be helpful in generating more accurate prediction models for the vaccination period.

Nigerian COVID-19 Incidence Modeling and Forecasting with Univariate Time Series Model

The occurrence of COVID-19 has given rise to dreadful medical difficulties due to its hyper-endemic effects on the human population. This made it fundamental to model and forecast COVID-19 pervasiveness and mortality to control the spread viably. The COVID-19 data used was from February, 28, 2020 to March 1, 2021. ARIMA(1,2,0) was selected for modeling COVID-19 confirmed and ARIMA(1,1,0) for death cases. The model was shown to be adequate for modeling and forecasting Nigerian COVID-19 data based on the ARIMA model building results. The forecasted values from the two models indicated Nigerian COVID-19 cumulative confirmed and death case continues to rise and maybe in-between 189,019–327,426 and interval 406–3043, respectively in the next 3 months (May 30, 2021). The ARIMA models forecast indicated an alarming rise in Nigerian COVID-19 confirmed and death cases on a daily basis. The findings indicated that effective treatment strategies must be put in place, the health sector should be monitored and properly funded. All the protocols and restrictions put in place by the NCDC, Nigeria should be clung to diminish the spread of the pandemic and possible mortality before immunizations that can forestall the infection is developed. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Time Series Analysis and Forecast of COVID-19 Pandemic

Background: The coronavirus has killed over 80 million individuals globally. Thus, the linear regression and autoregressive integrated moving average (ARIMA) model analyze the pattern of COVID-19 and identify the future confirmed cases. Methods: In this study, the dataset was used from the Johns Hopkins University (JHU CSSE) data repository in COVID-19 analytics package and prophet library. The time series analysis creates a simulating linear regression and ARIMA model for COVID-19 confirmed cases. The best fit model is select by Akaike information criteria (AIC) and predicts short-term issues validated by Ljung-Box Q test using RStudio Cloud. Results: The linear regression and ARIMA model identifies a best-fit model for time series data. From this model, forecast of more than 300,000 to 1,500,000 from 2020 to 2022. In addition, it depicts a significant increasing trend in the future predictions of confirmed cases. Conclusion: This forecast can help estimate the number of cases that information can provide control measures for an epidemic outbreak. It can suggest the government plan the policies regarding the control of the spread of the virus. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

DOES THE COVID-19 DISCRIMINATE BY GENDER? CROATIAN AND SLOVENIAN CASE

The paper aim is to investigate whether males or females are more likely to get infected by the COVID-19 disease. Due to the fact that the COVID-19 disease is a new disease about which a lot of things are not well known yet, in the analysis daily data from the one-year period from March 1, 2020 to February 28, 2021 are used. The comparison of total confirmed COVID-19 cases according to gender is conducted for Croatia and Slovenia. In addition, the comparison is conducted by taking into account age groups as well. © 2021 Samo Drobne – Lidija Zadnik Stirn – Mirjana Kljajić Borštnar – Janez Povh – Janez Žerovnik

How does Covid-19 affect global equity markets?

This study applies OLS, panel regression and Granger causality test to investigate the impact of the Coronavirus disease 2019 (Covid-19) outbreak on the global equity markets during the early stage of the pandemic. We find that the Covid-19 outbreak has a significant negative impact on the overall equity index return of the eight economies even at 0.1% significance level. Furthermore, the pandemic has a more significant impact on the European countries than on the East Asian economies. The results have three main implications. Firstly, policy makers should react fast to mitigate the impact of a crisis. Secondly, investors should be aware of an outbreak of disease or other risks and adjust their investments accordingly. Furthermore, the Covid-19 outbreak results in a shift of power from the west to the east.

Regression modeling and correlation analysis spread of COVID-19 data for Pakistan

This study presents a mathematical analysis of the coronavirus spread in Pakistan by analyzing the (COVID-19) situation in six provinces, including Gilgit Baltistan, Azad Jammu Kashmir and federal capital (seven zones) individually. The influence of each province and the Federal Capital territory is then observed over the other territories. By subdividing the associated data into confirmed cases, death cases, and recovery cases, the dependence of the (COVID-19) situation from one province to the other provinces is investigated. Since the worsening circumstance in the neighboring countries were considered as a catalyst to initiate the outburst in Pakistan, it seemed necessary to have an understanding of the situation in neighboring countries, particularly, Iran, India, and Bangladesh. Exploratory data analysis is utilized to understand the behavior of confirmed cases, death cases, and recovery cases data of (COVID-19) in Pakistan. Also, an understanding of the pandemic spread during different waves of (COVID-19) is obtained. Depending on the individual situation in each of the provinces, it is expected to have a different ARIMA model in each case. Hunt for the most suitable ARIMA models is an essential part of this study. The time-series data forecasts by processing the most suitable ARIMA models to observe the influence of one territory over the other. Moreover, forecasting for the month of August 2021 is performed and a possible correlation with actual data is determined. Linear, multiple regression, and exponential models have been applied and the best-fitted model is acquired. The information obtained from such analysis can be employed to vary possible parameters and variables in the system to achieve optimal performance. © 2022 The Authors.

A Global Survey of Technological Resources and Datasets on COVID-19

—The application and successful utilization of technological resources in developing solutions to health, safety, and economic issues caused by COVID-19 indicate the importance of technology in curbing COVID-19. Also, the medical field has had to race against tie to develop and distribute the COVID-19 vaccine. This endeavour became successful with the vaccines created and approved in less than a year, a feat in medical history. Currently, much work is being done on data collection, where all significant factors impacting the disease are recorded. These factors include confirmed cases, death rates, vaccine rates, hospitalization data, and geographic regions affected by the pandemic. Continued research and use of technological resources are highly recommendable—the paper surveys list of packages, applications and datasets used to analyse COVID-19 © 2022, International Journal of Advanced Computer Science and Applications. All Rights Reserved.