COVID-19 contagion forecasting framework based on curve decomposition and evolutionary artificial neural networks: A case study in Andalusia, Spain

作者：

Highlights：

• Estimated polynomial model coefficients serve as COVID19 contagion rate descriptors.

• EANNs are used to build valid predictors for different pandemic stages.

• Considering curve polynomial descriptors significantly improve the model performances.

• Simultaneous Multi-Task EANN forecast perform better in Málaga with simpler models.

摘要

•Estimated polynomial model coefficients serve as COVID19 contagion rate descriptors.•EANNs are used to build valid predictors for different pandemic stages.•Considering curve polynomial descriptors significantly improve the model performances.•Simultaneous Multi-Task EANN forecast perform better in Málaga with simpler models.

论文关键词：COVID-19 contagion forecasting,Curve decomposition,Evolutionary artificial neural networks,Time series

论文评审过程：Received 31 January 2022, Revised 17 June 2022, Accepted 22 June 2022, Available online 27 June 2022, Version of Record 2 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117977