Real-time measurement of the uncertain epidemiological appearances of COVID-19 infections

Advanced forecasting of COVID-19 epidemic: Leveraging ensemble models, advanced optimization, and decomposition techniques

In the global effort to address the outbreak of the new coronavirus pneumonia (COVID-19) pandemic, accurate forecasting of epidemic patterns has become crucial for implementing successful interventions aimed at preventing and controlling the spread of the disease. The correct prediction of the course of COVID-19 outbreaks is a complex and challenging task, mainly because of the significant volatility in the data series related to COVID-19. Previous studies have been limited by the exclusive use of individual forecasting techniques in epidemic modeling, disregarding the integration of diverse prediction procedures. The lack of attention to detail in this situation can yield worse-than-ideal results. Consequently, this study introduces a novel ensemble framework that integrates three machine learning methods (kernel ridge regression (KRidge), Deep random vector functional link (dRVFL), and ridge regression) within a linear relationship (L-KRidge-dRVFL-Ridge). The optimization of this framework is accomplished through a distinctive approach, specifically adaptive differential evolution and particle swarm optimization (A-DEPSO). Moreover, an effective decomposition method, known as time-varying filter empirical mode decomposition (TVF-EMD), is employed to decompose the input variables. A feature selection technique, specifically using the light gradient boosting machine (LGBM), is also implemented to extract the most influential input variables. The daily datasets of COVID-19 collected from two countries, namely Italy and Poland, were used as the experimental examples. Additionally, all models are implemented to forecast COVID-19 at two-time horizons: 10- and 14-day ahead (t+10 and t+14). According to the results, the proposed model can yield higher correlation coefficient (R) for both case studies: Italy (t+10 = 0.965, t+14 = 0.961) and Poland (t+10 = 0.952, t+14 = 0.940) than the other models. The experimental results demonstrate that the model suggested in this paper has outstanding results in various kinds of complex epidemic prediction situations. The proposed ensemble model demonstrates exceptional accuracy and resilience, outperforming all similar models in terms of efficacy.

FCMCPS-COVID: AI propelled fog-cloud inspired scalable medical cyber-physical system, specific to coronavirus disease

Medical cyber-physical systems (MCPS) firmly integrate a network of medical objects. These systems are highly efficacious and have been progressively used in the Healthcare 4.0 to achieve continuous high-quality services. Healthcare 4.0 encompasses numerous emerging technologies and their applications have been realized in the monitoring of a variety of virus outbreaks. As a growing healthcare trend, coronavirus disease (COVID-19) can be cured and its spread can be prevented using MCPS. This virus spreads from human to human and can have devastating consequences. Moreover, with the alarmingly rising death rate and new cases across the world, there is an urgent need for continuous identification and screening of infected patients to mitigate their spread. Motivated by the facts, we propose a framework for early detection, prevention, and control of the COVID-19 outbreak by using novel Industry 5.0 technologies. The proposed framework uses a dimensionality reduction technique in the fog layer, allowing high-quality data to be used for classification purposes. The fog layer also uses the ensemble learning-based data classification technique for the detection of COVID-19 patients based on the symptomatic dataset. In addition, in the cloud layer, social network analysis (SNA) has been performed to control the spread of COVID-19. The experimental results reveal that compared with state-of-the-art methods, the proposed framework achieves better results in terms of accuracy (82.28 %), specificity (91.42 %), sensitivity (90 %) and stability with effective response time. Furthermore, the utilization of CVI-based alert generation at the fog layer improves the novelty aspects of the proposed system.

SIRSi-vaccine dynamical model for the Covid-19 pandemic

Covid-19, caused by severe acute respiratory syndrome coronavirus 2, broke out as a pandemic during the beginning of 2020. The rapid spread of the disease prompted an unprecedented global response involving academic institutions, regulatory agencies, and industries. Vaccination and nonpharmaceutical interventions including social distancing have proven to be the most effective strategies to combat the pandemic. In this context, it is crucial to understand the dynamic behavior of the Covid-19 spread together with possible vaccination strategies. In this study, a susceptible-infected-removed-sick model with vaccination (SIRSi-vaccine) was proposed, accounting for the unreported yet infectious. The model considered the possibility of temporary immunity following infection or vaccination. Both situations contribute toward the spread of diseases. The transcritical bifurcation diagram of alternating and mutually exclusive stabilities for both disease-free and endemic equilibria were determined in the parameter space of vaccination rate and isolation index. The existing equilibrium conditions for both points were determined in terms of the epidemiological parameters of the model. The bifurcation diagram allowed us to estimate the maximum number of confirmed cases expected for each set of parameters. The model was fitted with data from São Paulo, the state capital of SP, Brazil, which describes the number of confirmed infected cases and the isolation index for the considered data window. Furthermore, simulation results demonstrate the possibility of periodic undamped oscillatory behavior of the susceptible population and the number of confirmed cases forced by the periodic small-amplitude oscillations in the isolation index. The main contributions of the proposed model are as follows: A minimum effort was required when vaccination was combined with social isolation, while additionally ensuring the existence of equilibrium points. The model could provide valuable information for policymakers, helping define disease prevention mitigation strategies that combine vaccination and non-pharmaceutical interventions, such as social distancing and the use of masks. In addition, the SIRSi-vaccine model facilitated the qualitative assessment of information regarding the unreported infected yet infectious cases, while considering temporary immunity, vaccination, and social isolation index.

An analytical tool to support public policies and isolation barriers against SARS-CoV-2 based on mobility patterns and socio-economic aspects

It is crucial to develop spatiotemporal analysis tools to mitigate risks during a pandemic. Many dashboards encountered in the literature do not consider how the geolocation characteristics and travel patterns may influence the spread of the virus. This work brings an interactive tool that is capable of crossing information about mobility patterns, geolocation characteristics and epidemiologic variables. To do so, our system uses a mobility network, generated through anonymized mobile location data, which enables the division of a region into representative clusters. The clusters' aggregated socioeconomic, and epidemiologic indicators can be analyzed through multiple coordinated views. The proposal is to enable users to understand how different locations commute citizens, monitor risk over time, and understand what locations need more assistance, considering different layers of visualization, such as clusters and individual locations. The main novelty is the interactive way to construct the mobility network that defines the social distancing level and the way that risks are managed, since many different geolocation characteristics can be considered and visualized, such as socioeconomic indicators of a location, the economic importance of a set of locations, and the connection of important neighborhoods of a city with other cities. The proposed tool was built and verified by experts assembled to give scientific recommendations to the city administration of Recife, the capital city of Pernambuco. Our analysis shows how a policymaker could use the tool to evaluate different isolation scenarios considering the trade-off between economic activity and contamination risk, where the practical insights can also be used to tighten and relax mitigation measures in other phases of a pandemic.

Self-regulation of light emission of an AlGaInP quantum well diode

When an AlGaInP quantum well (QW) diode is biased with a forward voltage and illuminated with an external shorter-wavelength light beam, the diode is in a superposition state of both light emission and detection. The two different states take place simultaneously, and both the injected current and the generated photocurrent begin to mix. Here, we make use of this intriguing effect and integrate an AlGaInP QW diode with a programmed circuit. The AlGaInP QW diode with the dominant emission peak wavelength centered around 629.5 nm is excited by a 620-nm red-light source. The photocurrent is then extracted as a feedback signal to regulate the light emission of the QW diode in real time without an external or monolithically integrated photodetector, paving a feasible way to autonomously adjust the brightness of the QW diode for intelligent illumination in response to changes in the environmental light condition.

The role of machine learning in health policies during the COVID-19 pandemic and in long COVID management

The ongoing COVID-19 pandemic is arguably one of the most challenging health crises in modern times. The development of effective strategies to control the spread of SARS-CoV-2 were major goals for governments and policy makers. Mathematical modeling and machine learning emerged as potent tools to guide and optimize the different control measures. This review briefly summarizes the SARS-CoV-2 pandemic evolution during the first 3 years. It details the main public health challenges focusing on the contribution of mathematical modeling to design and guide government action plans and spread mitigation interventions of SARS-CoV-2. Next describes the application of machine learning methods in a series of study cases, including COVID-19 clinical diagnosis, the analysis of epidemiological variables, and drug discovery by protein engineering techniques. Lastly, it explores the use of machine learning tools for investigating long COVID, by identifying patterns and relationships of symptoms, predicting risk indicators, and enabling early evaluation of COVID-19 sequelae.

Data-driven analysis and predictive modeling on COVID-19

The coronavirus (COVID-19) started in China in 2019, has spread rapidly in every single country and has spread in millions of cases worldwide. This paper presents a proposed approach that involves identifying the relative impact of COVID-19 on a specific gender, the mortality rate in specific age, investigating different safety measures adopted by each country and their impact on the virus growth rate. Our study proposes data-driven analysis and prediction modeling by investigating three aspects of the pandemic (gender of patients, global growth rate, and social distancing). Several machine learning and ensemble models have been used and compared to obtain the best accuracy. Experiments have been demonstrated on three large public datasets. The motivation of this study is to propose an analytical machine learning based model to explore three significant aspects of COVID-19 pandemic as gender, global growth rate, and social distancing. The proposed analytical model includes classic classifiers, distinctive ensemble methods such as bagging, feature based ensemble, voting and stacking. The results show a superior prediction performance comparing with the related approaches.

Analysis of the socioeconomic impact due to COVID-19 using a deep clustering approach

One of the main problems that countries are currently having is being able to measure the impact of the pandemic in other areas of society (for example, economic or social). In that sense, being able to combine variables about the behavior of COVID-19 with other variables in the environment, to build models about its impact, which help the decision-making of national authorities, is a current challenge. In this sense, this work proposes an approach that allows monitoring the socioeconomic behavior of the regions/departments of a country (in this case, Colombia) due to the effect of COVID-19. To do this, an approach is proposed in which the behavior of the infected is initially predicted, and together with other context variables (climate, economics and socials) determines the current socioeconomic situation of a region. This classification of a region, with the pattern that characterizes it, is a fundamental input for those who make decisions. Thus, this work presents an approach based on machine learning techniques to identify regions with similar socioeconomic behaviors due to COVID-19, so they should eventually have similar public policies. The proposed hybrid model initially consists of a time series prediction model of infected, to which are added several context variables (climate, socioeconomic, incidence of COVID-19 at the level of deaths, suspects, etc.) in an unsupervised learning model, to determine the socioeconomic impact in the regions. Particularly, the unsupervised model groups similar regions together, and the pattern of each group describes the socioeconomic similarities between them, to help decision-makers in the process of defining policies to be implemented in the regions. The experiments showed the ability of the hybrid model to follow the evolution of the regions after 4 weeks. The quality metrics for the predictive model were around the values of 0.35 for MAPE and 0.68 for R 2 , and in the case of the clustering model were around the values of 0.3 for the Silhouette index and 0.6 for the Davies-Boulding index. The hybrid model allowed determining things like some regions that initially belonged to a group with a very low incidence of positive cases and very unfavorable socioeconomic conditions, became part of groups with moderately high incidences. Our preliminary results are very satisfactory since they allow studying the evolution of the socioeconomic impact in each region/department.

Deep learning modelling of public's sentiments towards temporal evolution of COVID-19 transmission

Public sentiments towards global pandemics are important for public health assessment and disease control. This study develops a modularized deep learning framework to quantify public sentiments towards COVID-19, followed by leveraging the predicted sentiments to model and forecast the daily growth rate of confirmed COVID-19 cases globally, via a proposed G parameter. In the proposed framework, public sentiments are first modeled via a valence dimensional indicator, instead of discrete schemas, and are classified into 4 primary emotional categories: (a) neutral; (b) negative; (c) positive; (d) ambivalent, by using multiple word embedding models and classifiers for text sentiments analyses and classification. The trained model is subsequently applied to analyze large volumes (millions in quantity) of daily Tweets pertaining to COVID-19, ranging from 22 Jan 2020 to 10 May 2020. The results demonstrate that the global community gradually evokes both positive and negative sentiments towards COVID-19 over time compared to the dominant neural emotion at its inception. The predicted time-series sentiments are then leveraged to train a deep neural network (DNN) to model and forecast the G parameter by achieving the lowest possible mean absolute percentage error (MAPE) score of around 17.0% during the model's testing step with the optimal model configuration.

Forecasting daily Covid-19 cases in the world with a hybrid ARIMA and neural network model

The use of models to predict disease cases is common in epidemiology and related areas, in the context of Covid-19, both ARIMA and Neural Network models can be applied for purposes of optimized resource management, so the aim of this study is to capture the linear and non-linear structures of daily Covid-19 cases in the world by using a hybrid forecasting model. In summary, the proposed hybrid system methodology consists of two steps. In the first step, an ARIMA model is used to analyze the linear part of the problem. In the second step, a neural network model is developed to model the residuals of the ARIMA model, which would be the non-linear part of it. The neural network model was superior to the ARIMA when considering the capture of weekly seasonality and in two weeks, the combination of models with the capture of seasonality in two weeks provided a mixed model with good error metrics, that allows actions to be premeditated with greater certainty, such as increasing the number of nurses in a location, or the acceleration of vaccination campaigns to diminish a possible increase in the number of cases.

Modeling the change in European and US COVID-19 death rates

Motivated by several possible differences in Covid-19 virus strains, age demographics, and face mask wearing between continents and countries, we focussed on changes in Covid death rates in 2020. We have extended our Covid-19 multicompartment model (Khan et al., 2020) to fit cumulative case and death data for 49 European countries and 52 US states and territories during the recent pandemic, and found that the case mortality rate had decreased by at least 80% in most of the US and at least 90% in most of Europe. We found that death rate decreases do not have strong correlations to other model parameters (such as contact rate) or other standard state/national metrics such as population density, GDP, and median age. Almost all the decreases occurred between mid-April and mid-June 2020, which corresponds to the time when many state and national lockdowns were relaxed resulting in surges of new cases. We examine here several plausible causes for this drop—improvements in treatment, face mask wearing, new virus strains, testing, potentially changing demographics of infected patients, and changes in data collection and reporting—but none of their effects are as significant as the death rate changes suggest. In conclusion, this work shows that a two death rate model is effective in quantifying the reported drop in death rates.

Predicting Corona Virus Affected Patients Using Supervised Machine Learning

The world is infected from the deadliest pandemic disease humankind has ever seen. Several medical practitioners have been encountered with the corona virus and are constantly losing their lives in the fight. Hence, the main objective of this research work is to characterize the clinical features of the patients and construct a novel dataset for machine learning to classify them accurately prior to treatment. The positive patients can be identified on many characteristics and the principle data for this research is considered on the basis of the exploratory analysis done on the various risk factors that is also associated with the mortality in the hospitals. As an outcome, this article presents a supervised machine learning model incorporating the insights, symptoms and classification of the corona virus infected person. The proposed model and the dataset are tested against six well known classifiers on various levels of cross folding and percentage splits. The proposed dataset is also tested against the actual patient records and was found that the model accurately categorizes them prior to their treatment. The experimental results for proposed techniques showed higher performance and better accuracy further creating an impact on then identification of corona virus patients.

Artificial intelligence for forecasting and diagnosing COVID-19 pandemic: A focused review

The outbreak of novel corona virus 2019 (COVID-19) has been treated as a public health crisis of global concern by the World Health Organization (WHO). COVID-19 pandemic hugely affected countries worldwide raising the need to exploit novel, alternative and emerging technologies to respond to the emergency created by the weak health-care systems. In this context, Artificial Intelligence (AI) techniques can give a valid support to public health authorities, complementing traditional approaches with advanced tools. This study provides a comprehensive review of methods, algorithms, applications, and emerging AI technologies that can be utilized for forecasting and diagnosing COVID-19. The main objectives of this review are summarized as follows. (i) Understanding the importance of AI approaches such as machine learning and deep learning for COVID-19 pandemic; (ii) discussing the efficiency and impact of these methods for COVID-19 forecasting and diagnosing; (iii) providing an extensive background description of AI techniques to help non-expert to better catch the underlying concepts; (iv) for each work surveyed, give a detailed analysis of the rationale behind the approach, highlighting the method used, the type and size of data analyzed, the validation method, the target application and the results achieved; (v) focusing on some future challenges in COVID-19 forecasting and diagnosing.

Coronavirus fake news detection via MedOSINT check in health care official bulletins with CBR explanation: The way to find the real information source through OSINT, the verifier tool for official journals

This research aims to design and prototype a tool to perform intelligence on open sources (OSINT), specifically on official medical bulletins for the detection of false news. MedOSINT is a modular tool that can be adapted to process information from different medical official bulletins. From the processed information, intelligence is generated for decision making, validating the veracity of the COVID-19 news. The tool is compared with other options and it is verified that MedOSINT outperforms the current options when analyzing official bulletins. Moreover, it is complemented with an expert explanation provided by a Case-Based Reasoning (CBR) system. This is proved to be an ideal complement because it can find explanatory cases for an explanation-by-example justification.

Seesaw scenarios of lockdown for COVID-19 pandemic: Simulation and failure analysis

The ongoing COVOD-19(SARS-CoV-2) outbreak has had a devastating impact on the economy, education and businesses. In this paper, the behavior of an epidemic is simulated on different contact networks. Herein, it is assumed that the infection may be transmitted at each contact from an infected person to a susceptible individual with a given probability. The probability of transmitting the disease may change due to the individuals' social behavior or interventions prescribed by the authorities. We utilized simulation on the contact networks to demonstrate how seesaw scenarios of lockdown can curb infection and level the pandemic without maximum pressure on the poor societies. Soft scenarios consist of closing businesses 2, 3, and 4 days in between with four levels of lockdown respected by 25%, 50%, 75%, and 100% of the population. The findings reveal that the outbreak can be flattened under softer alternatives instead of a doomsday scenario of complete lockdown. More specifically, it is turned out that proposed soft lockdown strategies can flatten up to 120% of the pandemic course. It is also revealed that transmission probability has a crucial role in the course of the infection, growth rate of the infection, and the number of infected individuals.

Factors Affecting COVID-19 Preventive Behaviors among University Students in Beijing, China: An Empirical Study Based on the Extended Theory of Planned Behavior

Higher education institutions (HEIs), among other social systems, have an irreplaceable role in combating COVID-19. However, we know little about institutional and individual factors that might facilitate university students' beliefs and behaviors toward preventive behaviors for COVID-19 within the higher education context. Our study applies an extended theory of planned behavior (TPB) model to investigate the structural relationships among the institutional climate, attitudes, subjective norms, perceived behavioral control and preventive behaviors of university students and to detect the moderating impacts of perceived risk on the structural model. Data were collected from 3693 university students at 18 universities in Beijing, China through an online survey. Structural equation modeling (SEM) and multigroup analysis were performed to examine the empirical model. The results reveal that (1) the institutional climate has a significant, direct effect on preventive behaviors for COVID-19 among university students, (2) the TPB components, namely attitudes, subjective norms and perceived behavioral control, partially mediate the relationship between the institutional climate and preventive behaviors for COVID-19, and (3) perceived risk moderates several paths in the model. Theoretical and practical implications are offered, and recommendations for future research are outlined.

Real-time prediction of COVID-19 patients health situations using Artificial Neural Networks and Fuzzy Interval Mathematical modeling

At the end of 2019, the SARS-CoV-2 virus caused an outbreak of COVID-19 disease. The spread of this once-in-a-century pathogen increases demand for appropriate medical care, which strains the capacity and resources of hospitals in a critical way. Given the limited time available to prepare for the required demand, health care administrators fear they will not be ready to face patient’s influx. To aid health managers with the Prioritization and Scheduling COVID-19 Patients problem, a tool based on Artificial Intelligence (AI) through the Artificial Neural Networks (ANN) method, and Operations Research (OR) through a Fuzzy Interval Mathematical model was developed. The results indicated that combining both models provides an effective assessment under scarce initial information to select a suitable list of patients for a set of hospitals. The proposed approach allows to achieve a key goal: minimizing death rates under each hospital constraints of available resources. Furthermore, there is a serious concern regarding the resurgence of the COVID-19 virus which could cause a more severe pandemic. Thus, the main outcome of this study is the application of the above-mentioned approaches, especially when combining them, as efficient tools serving health establishments to manage critical resources.

The Role of Artificial Intelligence in Fighting the COVID-19 Pandemic

The first few months of 2020 have profoundly changed the way we live our lives and carry out our daily activities. Although the widespread use of futuristic robotaxis and self-driving commercial vehicles has not yet become a reality, the COVID-19 pandemic has dramatically accelerated the adoption of Artificial Intelligence (AI) in different fields. We have witnessed the equivalent of two years of digital transformation compressed into just a few months. Whether it is in tracing epidemiological peaks or in transacting contactless payments, the impact of these developments has been almost immediate, and a window has opened up on what is to come. Here we analyze and discuss how AI can support us in facing the ongoing pandemic. Despite the numerous and undeniable contributions of AI, clinical trials and human skills are still required. Even if different strategies have been developed in different states worldwide, the fight against the pandemic seems to have found everywhere a valuable ally in AI, a global and open-source tool capable of providing assistance in this health emergency. A careful AI application would enable us to operate within this complex scenario involving healthcare, society and research.