Predictive Information Workflow of Forecasting Number of COVID-19 Confirmed Cases

There are questions about how to accurately prepare with the correct number of resources for distribution in order to properly manage the healthcare resources (e.g., healthcare workers, Masks, ART-19 TestKit) required to tighten the grip on the COVID-19 pandemic. Mathematical and computational forecasting models have well served the means to address these questions, as well as the resulting advisories to governments. A workflow is proposed in this research, aiming to develop a forecasting simulation that makes accurate predictions on COVID-19 confirmed cases in Singapore. According to the analysis of the prior works, six candidate forecasting models are evaluated and compared in the workflow: polynomial regression, linear regression, SVM, Prophet, Holt's linear, and LSTM models. The study's goal is to determine the most suitable forecasting model for COVID-19 cases in Singapore. Two algorithms are also proposed to better compute the performance of two models: the order algorithm to determine optimal degree order for the polynomial regression model, and the optimizing algorithm for the Holt's linear model to calculate the optimal smoothing parameters. Observed from the experiment results with the COVID-19 dataset, the Prophet method model achieves the best performance with the lowest Root Mean Square Error (RMSE) score of 1557.744836 and Mean Absolute Percentage Error (MAPE) score of 0.468827, compared to the other five models. The Prophet method model achieving average accuracy range of 90% when forecasting the number of confirmed COVID-19 cases in Singapore for the next 87 days ahead. is chosen and recommended to be used as a system model for forecast the COVID-19 confirm cases in Singapore. The developed workflow will greatly assist the authorities in taking timely actions and making decisions to contain the COVID-19 pandemic. © 2022 IEEE.

Sensing Social Media to Forecast COVID-19 Cases

Social media has become a key tool for spreading the news, discussing ideas and comments on world events, playing a relevant role also in public health management, especially in epidemics surveillance like seasonal flu. Online social media actually can provide an important help in monitoring disease spreading as users self-report their health-related issues. Since the very first days of COVID-19 outbreak, people exchanged news, updates, sentiment and opinion about the pandemics. The paper describes a study aiming at evaluating the correlation of tweets with official COVID-19 data. Based on the outcomes of the correlation study, the paper proposes a forecasting model to predict the number of new daily COVID-19 cases. The approach is formulated as an autoregressive model that combines tweets and official COVID-19 data. A real-word dataset of tweets is used for the correlation study and to evaluate the performance of the forecasting model. Results shown the feasibility of the approach, highlighting the improvement obtained when tweets are integrated in the forecasting model, allowing to predict new COVID-19 cases in advance, on average 4-6 days before they were confirmed.

Mathematical Modeling of COVID-19 Spread Using Genetic Programming Algorithm

This paper analyses the possibilities of using Machine learning to develop a forecasting model for COVID-19 with a publicly available dataset from the Johns Hopkins University COVID-19 Data Repository and with the addition of a percentage of each variant from the GISAID Variant database. Genetic programming (GP), a symbolic regressor algorithm, is used for the estimation of new confirmed infected cases, hospitalized cases, cases in intensive care units (ICUs), and deceased cases. This metaheuristics method algorithm was used on a dataset for Austria and neighboring countries Czechia, Hungary, Slovenia, and Slovakia. Machine learning was done to create individual models for each country. Variance-based sensitivity analysis was initiated using the obtained mathematical models. This analysis showed us which input variables the output of the obtained models is sensitive to, like in the case of how much each covid variant affects the spread of the virus or the number of deceased cases. Individual short-term models have achieved very high R2 scores, while long-term predictions have achieved lower R2 scores. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Novel Deep Learning Model For Hotel Demand and Revenue Prediction amid COVID-19

The COVID-19 pandemic has cast a substantial impact on the tourism and hospitality sector. Public policies such as travel restrictions and stay-at-home orders had significantly affected tourist activities and service businesses' operations and profitability. It is essential to develop interpretable forecasting models to support managerial and organizational decision-making. We developed DemandNet, a novel deep learning framework for predicting time series data under the influence of the COVID-19 pandemic. The DemandNet framework has the following unique characteristics. First, it selects the top static and dynamic features embedded in the time series data. Second, it includes a nonlinear model which can provide interpretable insight into the previously seen data. Third, a novel prediction model is developed to leverage the above characteristics to make robust long-term forecasts. We evaluated DemandNet using daily hotel demand and revenue data from eight cities in the US between 2013 and 2020. Our findings reveal that DemandNet outperforms the state-of-art models and can accurately predict the effect of the COVID-19 pandemic on hotel demand and revenue. © 2022 IEEE Computer Society. All rights reserved.

Real-Time Cold Chain Forecasting Model for Agricultural Logistic Transportation using Feature Centric Deep Neural Classification for Seasonal Recommendation

In recent days, cold chain logistic progression has been affected due to covid quarantine because real-time human resources being affected. Agriculture transportation and food safety are essential for human lives to avoid wastage of product. Analyzing the stock hold management needs more prediction accuracy in the seasonal recommendations for producing Agri-products. Increasing information and collaborative approaches in big data leads to more dimensions to analyze the prediction leads to inaccuracy for a recommendation. To improve the cold chain process, intend a Real-time Cold chain forecasting model for agricultural logistic transportation using feature centric deep neural classification for a seasonal recommendation. Initially, the preprocess was carried out to reduce the noise present in the seasonal collective and cold chain logistic dataset, which contains information about agriculture in stock detail, production, seasonal, and daily requirement ratio. The cold chain recommendation big data analytics estimate the seasonal productive margin factor (SPMF) and Stock hold production hit rate (SPHR) for feature logistic margins. Then selects the features using Intensive Agro feature successive rate (IAFSR) be grouped into clusters. Then the selected features are trained with Multi-objective Deep sub spectral neural network (MODS2NN) to categorize the needs of classes for recommendation. This cold chain process improves the prediction accuracy as well than other methods to recommendation the logistic stock hold management by right seasonal recommendation. © 2022 IEEE.

Epidemic Outbreak Prediction with Ensemble of Deep Learning Models

The ability of today's technology has proved it's significance and dire need in the world yet again, with COVID-19 being a global pandemic. Various techniques are being incorporated and researches being conducted everyday in order to mitigate this pandemic. Forecasting of COVID-19 cases is one such task in machine learning which is being researched intensively to develop reliable forecasting models.In the proposed work, we have forecasted the number of COVID-19 confirmed,recovered and death cases globally using time series data with machine learning and deep learning ensemble models. The purpose of this study is to prove that ensemble of several week learners that we have developed can result in a better performing model. Deep learning models always tend to perform better than machine learning and traditional linear models due to their non-linearity. Our study concludes that deep learning ensemble model achieves better performance than the machine learning ensemble (Random forest) and the individual base learners used in ensemble model itself in COVID-19 forecasting. © 2022 IEEE.

Using a Layered Ensemble of Physics-Guided Graph Attention Networks to Predict COVID-19 Trends

The COVID-19 pandemic has spread rapidly and significantly impacted most countries in the world. Providing an accurate forecast of COVID-19 at multiple scales would help inform public health decisions, but recent forecasting models are typically used at the state or country level. Furthermore, traditional mathematical models are limited by simplifying assumptions, while machine learning algorithms struggle to generalize to unseen trends. This motivates the need for hybrid machine learning models that integrate domain knowledge for accurate long-term prediction. We propose a three-layer, geographically informed ensemble, an extensive peer-learning framework, for predicting COVID-19 trends at the country, continent, and global levels. As the base layer, we develop a country-level predictor using a hybrid Graph Attention Network that incorporates a modified SIR model, adaptive loss function, and edge weights informed by mobility data. We aggregated 163 country GATs to train the continent and world MLP layers of the ensemble. Our results indicate that incorporating quantitatively accurate equations and real-world data to model inter-community interactions improves the performance of spatio-temporal machine learning algorithms. Additionally, we demonstrate that integrating geographic information (continent composition) improves the performance of the world predictor in our layered architecture. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Enhancing COVID-19 Ensemble Forecasting Model Performance Using Auxiliary Data Sources

Real-time forecasting of non-stationary time series is a challenging problem, especially when the time series evolves rapidly. For such cases, it has been observed that ensemble models consisting of a diverse set of model classes can perform consistently better than individual models. In order to account for the nonstationarity of the data and the lack of availability of training examples, the models are retrained in real-time using the most recent observed data samples. Motivated by the robust performance properties of ensemble models, we developed a Bayesian model averaging ensemble technique consisting of statistical, deep learning, and compartmental models for fore-casting epidemiological signals, specifically, COVID-19 signals. We observed the epidemic dynamics go through several phases (waves). In our ensemble model, we observed that different model classes performed differently during the various phases. Armed with this understanding, in this paper, we propose a modification to the ensembling method to employ this phase information and use different weighting schemes for each phase to produce improved forecasts. However, predicting the phases of such time series is a significant challenge, especially when behavioral and immunological adaptations govern the evolution of the time series. We explore multiple datasets that can serve as leading indicators of trend changes and employ transfer entropy techniques to capture the relevant indicator. We propose a phase prediction algorithm to estimate the phases using the leading indicators. Using the knowledge of the estimated phase, we selectively sample the training data from similar phases. We evaluate our proposed methodology on our currently deployed COVID-19 forecasting model and the COVID-19 ForecastHub models. The overall performance of the proposed model is consistent across the pandemic. More importantly, it is ranked second during two critical rapid growth phases in cases, regimes where the performance of most models from the ForecastHub dropped significantly. © 2022 IEEE.

Deep Neural Network Architectures for Momentary Forecasting in Dry Bulk Markets: Robustness to the Impact of COVID-19

The COVID-19 pandemic has severely affected various global markets, increasing the need for new forecasting models for the dry bulk market. Therefore, this study proposes deep neural network (abbreviated DNN) architectures to build a model for momentary forecasting that does not affect accuracy in the case of economic shocks (i.e., COVID-19) and elucidates the strategy for obtaining DNNs. First, since momentary and short-term forecastings are fundamentally different, they might use independent methods;as such, I apply DNN for the time series classification to momentary forecasting. Second, the proposed architecture is constructed by considering sparsity, because designing DNN architectures robust to any impacts is a type of overfitting prevention for deep neural networks. Finally, this study proposes indices for quantitatively evaluating the DNN architectures that represent the realized forecasting performance of various deep neural networks. Using these indices, I demonstrate that optimal architectures may need to have model sparsity in the DNN (i.e., sparsity independent of the input data). The importance of this issue has been demonstrated experimentally. As a result, the architectures achieved target performances of 88%, 91%, and 79% accuracy and had stability for Panamax, Supramax, and Capesize vessels, respectively from February 2016 to September 2021 (i.e., five years and eight months). It is difficult to identify a correlation between model performance and volatility. Furthermore, before and after the COVID-19 shock, the performance of the proposed models compared to the optimal one exceeds that of other four recent models, namely 'Facebook Prophet,' 'DARTS,' 'SKTIME,' and 'AutoTS'. © 2013 IEEE.

Comparison of ARIMA, ETS, NNAR, TBATS and hybrid models to forecast the second wave of COVID-19 hospitalizations in Italy.

The coronavirus disease (COVID-19) is a severe, ongoing, novel pandemic that emerged in Wuhan, China, in December 2019. As of January 21, 2021, the virus had infected approximately 100 million people, causing over 2 million deaths. This article analyzed several time series forecasting methods to predict the spread of COVID-19 during the pandemic's second wave in Italy (the period after October 13, 2020). The autoregressive moving average (ARIMA) model, innovations state space models for exponential smoothing (ETS), the neural network autoregression (NNAR) model, the trigonometric exponential smoothing state space model with Box-Cox transformation, ARMA errors, and trend and seasonal components (TBATS), and all of their feasible hybrid combinations were employed to forecast the number of patients hospitalized with mild symptoms and the number of patients hospitalized in the intensive care units (ICU). The data for the period February 21, 2020-October 13, 2020 were extracted from the website of the Italian Ministry of Health ( www.salute.gov.it ). The results showed that (i) hybrid models were better at capturing the linear, nonlinear, and seasonal pandemic patterns, significantly outperforming the respective single models for both time series, and (ii) the numbers of COVID-19-related hospitalizations of patients with mild symptoms and in the ICU were projected to increase rapidly from October 2020 to mid-November 2020. According to the estimations, the necessary ordinary and intensive care beds were expected to double in 10 days and to triple in approximately 20 days. These predictions were consistent with the observed trend, demonstrating that hybrid models may facilitate public health authorities' decision-making, especially in the short-term.

Airport terminal passenger forecast under the impact of COVID-19 outbreaks: A case study from China

Passengers significantly affect airport terminal energy consumption and indoor environmental quality. Accurate passenger forecasting provides important insights for airport terminals to optimize their operation and management. However, the COVID-19 pandemic has greatly increased the uncertainty in airport passenger since 2020. There are insufficient studies to investigate which pandemic-related variables should be considered in forecasting airport passenger trends under the impact of COVID-19 outbreaks. In this study, the interrelationship between COVID-19 pandemic trends and passenger traffic at a major airport terminal in China was analyzed on a day-by-day basis. During COVID-19 outbreaks, three stages of passenger change were identified and characterized, i.e., the decline stage, the stabilization stage, and the recovery stage. A typical "sudden drop and slow recovery” pattern of passenger traffic was identified. A LightGBM model including pandemic variables was developed to forecast short-term daily passenger traffic at the airport terminal. The SHapley Additive exPlanations (SHAP) values was used to quantify the contribution of input pandemic variables. Results indicated the inclusion of pandemic variables reduced the model error by 27.7% compared to a baseline model. The cumulative numbers of COVID-19 cases in previous weeks were found to be stronger predictors of future passenger traffic than daily COVID-19 cases in the most recent week. In addition, the impact of pandemic control policies and passengers' travel behavior was discussed. Our empirical findings provide important implications for airport terminal operations in response to the on-going COVID-19 pandemic. © 2022

LSTM and ARIMA for Forecasting COVID-19 Positive and Mortality Cases in DKI Jakarta and West Java

The spread of COVID-19 in Indonesia is still classified as a pandemic until October 31, 2022. Even though the endemic has been enforced in several nations worldwide. However, the fact that people's mobility is increasing means that this condition can increase the number of new cases of COVID-19. The Indonesian government remains vigilant about any decisions that will be taken to maintain the stability of the country's health sector, economy, and population mobility. First, The purpose of this our research is to forecast of daily positive confirmed and daily mortality for the next 13 days using COVID-19 epidemiological data in Indonesia, i.e. DKI Jakarta and West Java. Second, the forecasting model uses a deep learning approach, i.e. LSTM and ARIMA. furthermore, The LSTM method and ARIMA modeling results are compared based on their respective to regions. Finally, The LSTM method has good model performance and the ability to forecast COVID-19 cases based on RMSE and MAPE. © 2022 IEEE.

Impact on Air Quality Index of India Due to Lockdown.

For the very first time, on 22-March-2020 the Indian government forced the only known method at that time to prevent the outburst of the COVID-19 pandemic which was restricting the social movements, and this led to imposing lockdown for a few days which was further extended for a few months. As the impact of lockdown, the major causes of air pollution were ceased which resulted in cleaner blue skies and hence improving the air quality standards. This paper presents an analysis of air quality particulate matter (PM)2.5, PM10, Nitrogen Dioxide (NO2), and Air quality index (AQI). The analysis indicates that the PM10 AQI value drops impulsively from (40-45%), compared before the lockdown period, followed by NO2 (27-35%), Sulphur Dioxide (SO2) (2-10%), PM2.5 (35-40%), but the Ozone (O3) rises (12-25%). To regulate air quality, many steps were taken at national and regional levels, but no effective outcome was received yet. Such short-duration lockdowns are against economic growth but led to some curative effects on AQI. So, this paper concludes that even a short period lockdown can result in significant improvement in Air quality.

Best selected forecasting models for COVID-19 pandemic

This study sought to identify the most accurate forecasting models for COVID-19-confirmed cases, deaths, and recovered patients in Pakistan. For COVID-19, time series data are available from 16 April to 15 August 2021 from the Ministry of National Health Services Regulation and Coordination's health advice portal. Descriptive as well as time series models, autoregressive integrated moving average, exponential smoothing models (Brown, Holt, and Winters), neural networks, and Error, Trend, Seasonal (ETS) models were applied. The analysis was carried out using the R coding language. The descriptive analysis shows that the average number of confirmed cases, COVID-19-related deaths, and recovered patients reported each day were 2,916, 69.43, and 2,772, respectively. The highest number of COVID-19 confirmed cases and fatalities per day, however, were recorded on April 17, 2021 and April 27, 2021, respectively. ETS (M, N, M), neural network, nonlinear autoregressive (NNAR) (3, 1, 2), and NNAR (8, 1, 4) forecasting models were found to be the best among all other competing models for the reported confirmed cases, deaths, and recovered patients, respectively. COVID-19-confirmed outbreaks, deaths, and recovered patients were predicted to rise on average by around 0.75, 5.08, and 19.11% daily. These statistical results will serve as a guide for disease management and control.

Accuracy of COVID-19 evolution models for different forecast horizons

Currently, the statistics on COVID-19 for many regions are accumulated for the time span of over than two years, which facilitates the use of data-driven algorithms, such as neural networks, for prediction of the disease's further development. This article provides a comparative analysis of various forecasting models of COVID-19 dynamics. The forecasting is performed for the period from 07/20/2020 to 05/05/2022 using statistical data from the regions of the Russian Federation and the USA. The forecast target is defined as the sum of confirmed cases over the forecast horizon. Models based on the Exponential Smoothing (ES) method and deep learning methods based on Long Short-Term Memory (LSTM) units were considered. The training data set included the data from all regions available in the full data set. The MAPE metric was used for model comparison, the evaluation of the effectiveness of LSTM in the learning process was carried out using cross-validation on the mean squared error (MSE) metric. The comparisons were made with the models from various literature sources, as well as with the baseline model "tomorrow as today" (for which the sum of cases over the forecast horizon is supposed to be equal to the current case number multiplied by the forecast horizon length). It was shown that on small horizons (up to 28 days) the "tomorrow as today” model and ES algorithms show better accuracy than LSTM. In turn, on longer horizons (28 days or more), the preference should be given to the more complex LSTM-based model. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)

A scalable pipeline for COVID-19: the case study of Germany, Czechia and Poland

Throughout the coronavirus disease 2019 (COVID-19) pandemic, decision makers have relied on forecasting models to determine and implement non-pharmaceutical interventions (NPI). In building the forecasting models, continuously updated datasets from various stakeholders including developers, analysts, and testers are required to provide precise predictions. Here we report the design of a scalable pipeline which serves as a data synchronization to support inter-country top-down spatiotemporal observations and forecasting models of COVID-19, named the where2test, for Germany, Czechia and Poland. We have built an operational data store (ODS) using PostgreSQL to continuously consolidate datasets from multiple data sources, perform collaborative work, facilitate high performance data analysis, and trace changes. The ODS has been built not only to store the COVID-19 data from Germany, Czechia, and Poland but also other areas. Employing the dimensional fact model, a schema of metadata is capable of synchronizing the various structures of data from those regions, and is scalable to the entire world. Next, the ODS is populated using batch Extract, Transfer, and Load (ETL) jobs. The SQL queries are subsequently created to reduce the need for pre-processing data for users. The data can then support not only forecasting using a version-controlled Arima-Holt model and other analyses to support decision making, but also risk calculator and optimisation apps [1, 2]. The data synchronization runs at a daily interval, which is displayed at https://www.where2test.de. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

Sensing Social Media to Forecast COVID-19 Cases

Social media has become a key tool for spreading the news, discussing ideas and comments on world events, playing a relevant role also in public health management, especially in epidemics surveillance like seasonal flu. Online social media actually can provide an important help in monitoring disease spreading as users self-report their health-related issues. Since the very first days of COVID-19 outbreak, people exchanged news, updates, sentiment and opinion about the pandemics. The paper describes a study aiming at evaluating the correlation of tweets with official COVID-19 data. Based on the outcomes of the correlation study, the paper proposes a forecasting model to predict the number of new daily COVID-19 cases. The approach is formulated as an autoregressive model that combines tweets and official COVID-19 data. A real-word dataset of tweets is used for the correlation study and to evaluate the performance of the forecasting model. Results shown the feasibility of the approach, highlighting the improvement obtained when tweets are integrated in the forecasting model, allowing to predict new COVID-19 cases in advance, on average 4-6 days before they were confirmed. © 2022 IEEE.

Forecasting Model Based on Lifestyle Risk and Health Factors to Predict COVID-19 Severity.

The COVID-19 pandemic has now spread worldwide, becoming a real global health emergency. The main goal of this work is to present a framework for studying the impact of COVID-19 on Italian territory during the first year of the pandemic. Our study was based on different kinds of health features and lifestyle risk factors and exploited the capabilities of machine learning techniques. Furthermore, we verified through our model how these factors influenced the severity of the pandemics. Using publicly available datasets provided by the Italian Civil Protection, Italian Ministry of Health and Italian National Statistical Institute, we cross-validated the regression performance of a Random Forest model over 21 Italian regions. The robustness of the predictions was assessed by comparison with two other state-of-the-art regression tools. Our results showed that the proposed models reached a good agreement with data. We found that the features strongly associated with the severity of COVID-19 in Italy are the people aged over 65 flu vaccinated (24.6%) together with individual lifestyle behaviors. These findings could shed more light on the clinical and physiological aspects of the disease.

Monitoring Novel Corona Virus using Machine Learning

In this article, we are working on a new Pandemic Corona (COVID-19) virus. COVID-19 is an infectious disease that causes serious lung damage. COVID-19 causes a disease in humans and has killed many people around the world. However, the virus has been declared pandemic by the World Health Organization (WHO) and all countries are trying to control and block all locations. In particular, four standard forecasting models have been used: linear regression (LR), logistics regression (LOR) and polynomial regression. Many areas of application that require the identification and hierarchy of threats have long used automatic learning models. [1] Machine-based (ML) analysis methods have been shown to be useful in predicting preoperative outcomes and improving decision-making about future actions. Different forecasting methods are widely used to solve forecasting problems. The purpose of this study was to determine the function of COVID-19 research and machine learning applications and algorithms for various purposes [2]. © 2022 IEEE.

Analyzing and Forecasting Electricity Consumption During and After the Lockdown Using Nonparametric Statistical Tests and Machine Learning

The impacts of lockdown caused by the COVID-19 pandemic have dramatically changed our dealing with different lifestyles. Many countries-imposed restrictions and regulations that significantly affect the pattern of the environment and energy characterizations. In 2020, the reliability of the energy flow became crucial under lockdown situations and the changes in the electrical demand patterns. This study aims to analyze the hourly electricity usage during and after the lockdown of the COVID-19 pandemic in 2020 in Taif, Saudi Arabia and find a correlation between the lockdown and changes in consumption patterns by using nonparametric statistical tests. Moreover, a forecasting model, using the nonlinear autoregressive (NAR) artificial neural networks (ANN), is developed to predict hourly electricity consumption for a short term. The developed forecasting model considers a wide range of observations for more than 2100 hours to improve forecasting accuracy and reduce errors. This study can help decision-makers in the energy management sectors improve systems resilience and respond to shocks. © 2022 IISE Annual Conference and Expo 2022. All rights reserved.