All Models Are Useful: Bayesian Ensembling for Robust High Resolution COVID-19 Forecasting DOI Creative Commons
Aniruddha Adiga, Lijing Wang, Benjamin Hurt

et al.

Published: Aug. 12, 2021

Timely, high-resolution forecasts of infectious disease incidence are useful for policy makers in deciding intervention measures and estimating healthcare resource burden. In this paper, we consider the task forecasting COVID-19 confirmed cases at county level United States. Although multiple methods have been explored task, their performance has varied across space time due to noisy data inherent dynamic nature pandemic. We present a pipeline which incorporates probabilistic from statistical, machine learning mechanistic through Bayesian ensembling scheme, operational nearly 6 months serving local, state federal policymakers While showing that ensemble is least as good individual methods, also show each method contributes significantly different spatial regions points. compare our model's with other similar models being integrated into CDC-initiated Forecast Hub, better longer forecast horizons. Finally, describe how such used increase lead training scenario projections. Our work demonstrates real-time high resolution can be developed by integrating within performance-based support pandemic response.

Language: Английский

Factors Determining the Behavioral Intention of Using Food Delivery Apps during COVID-19 Pandemics DOI Creative Commons
Chaiyawit Muangmee, Sebastian Kot, Nusanee Meekaewkunchorn

et al.

Journal of theoretical and applied electronic commerce research, Journal Year: 2021, Volume and Issue: 16(5), P. 1297 - 1310

Published: April 14, 2021

The purpose of this study was to investigate the factors determining behavioral intention using food delivery apps (FDAs) during COVID-19 pandemics, under a case Bangkok, Thailand. necessitated by increased use FDAs lockdown; online transactions were considered important in preventing spread virus. used quantitative techniques involving structural equation model (SEM) evaluate effects exogenous variables on endogenous variables. Primary data collected from people who had installed and FDAs. findings indicated that performance expectancy, effort social influence, timeliness, task technology fit, perceived trust, safety significantly influence (BIU) pandemic. To end, should be intensified understand as it pertains usage.

Language: Английский

Citations

224
A review on COVID-19 forecasting models DOI Creative Commons
Iman Rahimi, Chen Fang, Amir H. Gandomi

et al.

Neural Computing and Applications, Journal Year: 2021, Volume and Issue: 35(33), P. 23671 - 23681

Published: Feb. 4, 2021

The novel coronavirus (COVID-19) has spread to more than 200 countries worldwide, leading 36 million confirmed cases as of October 10, 2020. As such, several machine learning models that can forecast the outbreak globally have been released. This work presents a review and brief analysis most important forecasting against COVID-19. presented in this study possesses two parts. In first section, detailed scientometric an influential tool for bibliometric analyses, which were performed on COVID-19 data from Scopus Web Science databases. For above-mentioned analysis, keywords subject areas are addressed, while classification models, criteria evaluation, comparison solution approaches discussed second section work. conclusion discussion provided final sections study.

Language: Английский

Citations

220
Comparison of ARIMA, ETS, NNAR, TBATS and hybrid models to forecast the second wave of COVID-19 hospitalizations in Italy DOI Creative Commons
Gaetano Perone

The European Journal of Health Economics, Journal Year: 2021, Volume and Issue: 23(6), P. 917 - 940

Published: Aug. 4, 2021

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

Language: Английский

Citations

81
Modeling and forecasting of COVID-19 using a hybrid dynamic model based on SEIRD with ARIMA corrections DOI Creative Commons
Maher Alaraj, Munir Majdalawieh, Nishara Nizamuddin

et al.

Infectious Disease Modelling, Journal Year: 2020, Volume and Issue: 6, P. 98 - 111

Published: Dec. 3, 2020

The outbreak of novel coronavirus (COVID-19) attracted worldwide attention. It has posed a significant challenge for the global economies, especially healthcare sector. Even with robust system, countries were not prepared ramifications COVID-19. Several statistical, dynamic, and mathematical models COVID-19 including SEIR model have been developed to analyze infection its transmission dynamics. objective this research is use public data study properties associated pandemic develop dynamic hybrid based on SEIRD ascertainment rate automatically selected parameters. proposed consists two parts: modified ARIMA models. We fit parameters against historical values infected, recovered deceased population divided by rate, which, in turn, also parameter model. Residuals first recovered, populations are then corrected using can input real-time provide long- short-term forecasts confidence intervals. was tested validated US COVID statistics dataset from Tracking Project. For validation, we unseen recent statistical data. five common measures estimate prediction ability: MAE, MSE, MLSE, Normalized MSE. proved great ability make accurate predictions patients. output be used government, private sectors, policymakers reduce health economic risks significantly improved consumer credit scoring.

Language: Английский

Citations

77
Application of machine learning in the prediction of COVID-19 daily new cases: A scoping review DOI Creative Commons
Soudeh Ghafouri‐Fard, Hossein Mohammad‐Rahimi, Parisa Motie

et al.

Heliyon, Journal Year: 2021, Volume and Issue: 7(10), P. e08143 - e08143

Published: Oct. 1, 2021

COVID-19 has produced a global pandemic affecting all over of the world. Prediction rate spread and modeling its course have critical impact on both health system policy makers. Indeed, making depends judgments formed by prediction models to propose new strategies measure efficiency imposed policies. Based nonlinear complex nature this disorder difficulties in estimation virus transmission features using traditional epidemic models, artificial intelligence methods been applied for spread. importance machine deep learning approaches spreading trend, present study, we review studies which used these predict number cases COVID-19. Adaptive neuro-fuzzy inference system, long short-term memory, recurrent neural network multilayer perceptron are among mostly regard. We compared performance several Root means squared error (RMSE), mean absolute (MAE), R

Language: Английский

Citations

61
The research on COVID-19 and economy from 2019 to 2020: analysis from the perspective of bibliometrics DOI Creative Commons
Nana Liu, Zeshui Xu, Marinko Škare

et al.

Oeconomia Copernicana, Journal Year: 2021, Volume and Issue: 12(2), P. 217 - 268

Published: June 30, 2021

Research background: The outbreak and spread of COVID-19 brought disastrous influences to the development human society, especially economy. Purpose article: Considering that knowing about situations existing studies economy is not only helpful understand research progress connections between economy, but also provides effective suggestions for fighting against protecting this paper analyzes on from perspective bibliometrics. Methods: Firstly, discussion starts statistical analysis, in which basic distributions different countries/regions, publication sources, years, etc., are presented. Then, shows cooperation researchers analyzing related citation networks, co-citation networks networks. Further, theme analysis presented, co-occurrence shown, then detailed analyses introduced. Based these analyses, discussions future finally we draw a conclusion. Findings & value added: present situation Economy, show trends, can provide meaningful expectations.

Language: Английский

Citations

58
Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach DOI Creative Commons
Lu‐Yu Zhou, Chun Zhao, Ning Liu

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 122, P. 106157 - 106157

Published: March 16, 2023

Individuals in any country are badly impacted both economically and physically whenever an epidemic of infectious illnesses breaks out. A novel coronavirus strain was responsible for the outbreak sickness 2019. Corona Virus Disease 2019 (COVID-19) is name that World Health Organization (WHO) officially gave to pneumonia caused by on February 11, 2020. The use models informed machine learning currently a major focus study field improved forecasting. By displaying annual trends, forecasting can be performing impact assessments potential outcomes. In this paper, proposed forecast consisting time series such as long short-term memory (LSTM), bidirectional (Bi-LSTM), generalized regression unit (GRU), dense-LSTM have been evaluated prediction confirmed cases, deaths, recoveries 12 countries affected COVID-19. Tensorflow1.0 used programming. Indices known mean absolute error (MAE), root means square (RMSE), Median Absolute Error (MEDAE) r2 score utilized process evaluating performance models. We presented various ways time-series making LSTM (LSTM, BiLSTM), we compared these methods other evaluate Our suggests based among most advanced data.

Language: Английский

Citations

41
A Review on COVID-19 Forecasting Models DOI Creative Commons
Iman Rahimi, Fang Chen, Amir H. Gandomi

et al.

Research Square (Research Square), Journal Year: 2020, Volume and Issue: unknown

Published: Sept. 29, 2020

Abstract The Novel coronavirus (COVID-19) has distributed to more than 200 territory worldwide leading about 24 million confirmed cases as of August 25, 2020. Several models have been released that forecast the outbreak globally. This work presents a review most important forecasting against COVID-19 and shows short analysis each one. presented in this study possesses two parts. A detailed scientometric was done first section provides an influential tool for describing bibliometric analyses. performed on data corresponding using Scopus Web Science databases. For analysis, keywords subject areas were addressed while classification models, criteria evaluation comparison solution approaches second work. Conclusion discussion are provided final sections study.

Language: Английский

Citations

67
The COVID-19 pandemic impact upon housing brokers’ workflow and their clients’ attitude: Real estate market in Krakow DOI Creative Commons
Bartłomiej Marona, Mateusz Tomal

Entrepreneurial Business and Economics Review, Journal Year: 2020, Volume and Issue: 8(4), P. 221 - 232

Published: Jan. 1, 2020

Objective: The objective of the article is to assess impact COVID-19 pandemic upon workflow real estate brokers and their clients' attitude as exemplified by market in Krakow. Research Design & Methods: For purpose assessing aspects under consideration, a survey questionnaire with open-ended questions was distributed amongst all associated Małopolska Real Estate Brokers Association. Findings: findings indicate that has had considerable attitude. began render online services greater extent, thus they intensified use digital technologies running businesses. On other hand, clients like landlords numerous cases changed strategies, i.e. from short-term rental into long-term one. In turn, tenants demand lower rents higher standards apartments. Implications Recommendations: conducted studies have made it plausible state significant market. However, bears noting we do not conclude what extent those changes are permanent, therefore need for further studies. Contribution Value Added: This counts among first ones world address issue COVID-19's housing

Language: Английский

Citations

59
COVID-19 and digital deprivation in Poland DOI Creative Commons
Marta Kuc‐Czarnecka

Oeconomia Copernicana, Journal Year: 2020, Volume and Issue: 11(3), P. 415 - 431

Published: Sept. 17, 2020

Research background: The problem of digital deprivation is already known, but the COVID-19 pandemic has highlighted its negative consequences. A global change in way life, work and socialisation resulting from epidemic indicated that a basic level integration becoming necessary. During lockdown, people were forced to use ICTs adapt rapidly changing reality. Current experience with coronavirus shows transition these extraordinary circumstances not smooth. inability rapid conversion online world (due lack skills or technical capabilities) significantly reduces professional mobility, hinders access public services, case children, exposes them risk remaining outside remote education system. Purpose article: This research paper addressing new issues impact on deepening increasing severity e-exclusion. goal indicate territorial areas Poland which are particularly vulnerable due infrastructural deficiencies. Methods: Raster data regarding landform, combined vector population density type buildings as well location BTS stations used so-called modelling overland paths (GIS method) divide. Findings & Value added: showed 4% Poles remain out-side Internet coverage, additional ten percent out reach Internet, allowing efficient learning. 'accessibility gap' underestimated. E-exclusion become pressing issue requires urgent system solutions, future lockdowns.

Language: Английский

Citations

56