The purpose of the chapter is using machine learning techniques (namely Self-Organizing Maps) to catch the emergence of clusters among Italian regions that can eventually contribute to explain the different behaviour of the pandemic within the same country. To do this, we have considered demographic, healthcare, and political data at regional level and we have tried going to the root of interactions among them. In this way, we obtained a model of the relations among variables with good explanatory capabilities, a kind of early-warning system which we hope could be helpful to address further intervention in the battle against COVID-19 pandemic.
Pandemic Spreading in Italy and Regional Policies: An Approach with Self-organizing Maps
Marina Resta
2022-01-01
Abstract
The purpose of the chapter is using machine learning techniques (namely Self-Organizing Maps) to catch the emergence of clusters among Italian regions that can eventually contribute to explain the different behaviour of the pandemic within the same country. To do this, we have considered demographic, healthcare, and political data at regional level and we have tried going to the root of interactions among them. In this way, we obtained a model of the relations among variables with good explanatory capabilities, a kind of early-warning system which we hope could be helpful to address further intervention in the battle against COVID-19 pandemic.File | Dimensione | Formato | |
---|---|---|---|
2021 MResta Pandemic Spreading in Italy.pdf
accesso chiuso
Tipologia:
Documento in versione editoriale
Dimensione
10.12 MB
Formato
Adobe PDF
|
10.12 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.