A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain

This work proposes a semi-parametric approach to estimate the evolution of COVID-19 (SARS-CoV-2) in Spain. Considering the sequences of 14-day cumulative incidence of all Spanish regions, it combines modern Deep Learning (DL) techniques for analyzing sequences with the usual Bayesian Poisson-Gamma m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Stefano Cabras
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	applied Bayesian methods COVID-19 Deep Learning Multivariate Time Series LSTM SARS-CoV-2 Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/dc424874f2aa4618a1bb441a35bb266b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dc424874f2aa4618a1bb441a35bb266b
record_format	dspace
spelling	oai:doaj.org-article:dc424874f2aa4618a1bb441a35bb266b2021-11-25T18:17:13ZA Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain10.3390/math92229212227-7390https://doaj.org/article/dc424874f2aa4618a1bb441a35bb266b2021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/22/2921https://doaj.org/toc/2227-7390This work proposes a semi-parametric approach to estimate the evolution of COVID-19 (SARS-CoV-2) in Spain. Considering the sequences of 14-day cumulative incidence of all Spanish regions, it combines modern Deep Learning (DL) techniques for analyzing sequences with the usual Bayesian Poisson-Gamma model for counts. The DL model provides a suitable description of the observed time series of counts, but it cannot give a reliable uncertainty quantification. The role of expert elicitation of the expected number of counts and its reliability is DL predictions’ role in the proposed modelling approach. Finally, the posterior predictive distribution of counts is obtained in a standard Bayesian analysis using the well known Poisson-Gamma model. The model allows to predict the future evolution of the sequences on all regions or estimates the consequences of eventual scenarios.Stefano CabrasMDPI AGarticleapplied Bayesian methodsCOVID-19Deep LearningMultivariate Time SeriesLSTMSARS-CoV-2MathematicsQA1-939ENMathematics, Vol 9, Iss 2921, p 2921 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	applied Bayesian methods COVID-19 Deep Learning Multivariate Time Series LSTM SARS-CoV-2 Mathematics QA1-939
spellingShingle	applied Bayesian methods COVID-19 Deep Learning Multivariate Time Series LSTM SARS-CoV-2 Mathematics QA1-939 Stefano Cabras A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain
description	This work proposes a semi-parametric approach to estimate the evolution of COVID-19 (SARS-CoV-2) in Spain. Considering the sequences of 14-day cumulative incidence of all Spanish regions, it combines modern Deep Learning (DL) techniques for analyzing sequences with the usual Bayesian Poisson-Gamma model for counts. The DL model provides a suitable description of the observed time series of counts, but it cannot give a reliable uncertainty quantification. The role of expert elicitation of the expected number of counts and its reliability is DL predictions’ role in the proposed modelling approach. Finally, the posterior predictive distribution of counts is obtained in a standard Bayesian analysis using the well known Poisson-Gamma model. The model allows to predict the future evolution of the sequences on all regions or estimates the consequences of eventual scenarios.
format	article
author	Stefano Cabras
author_facet	Stefano Cabras
author_sort	Stefano Cabras
title	A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain
title_short	A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain
title_full	A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain
title_fullStr	A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain
title_full_unstemmed	A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain
title_sort	bayesian-deep learning model for estimating covid-19 evolution in spain
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/dc424874f2aa4618a1bb441a35bb266b
work_keys_str_mv	AT stefanocabras abayesiandeeplearningmodelforestimatingcovid19evolutioninspain AT stefanocabras bayesiandeeplearningmodelforestimatingcovid19evolutioninspain
_version_	1718411410250137600

A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain

Ejemplares similares