期刊
MATHEMATICS
卷 9, 期 22, 页码 -出版社
MDPI
DOI: 10.3390/math9222921
关键词
applied Bayesian methods; COVID-19; Deep Learning; Multivariate Time Series; LSTM; SARS-CoV-2
类别
资金
- MINECO-Spain [PID2019-104790GB-I00]
This approach combines deep learning techniques and a Bayesian model to estimate the evolution of COVID-19 in Spain, providing a suitable description of count time series and predicting future evolution or consequences of scenarios.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据