<> "The repository administrator has not yet configured an RDF license."^^ . <> . . . "Simulation of Covid-19 epidemic evolution:\r\nare compartmental models really predictive?"^^ . "Computational models for the simulation ofthe severe acute respiratory syndrome\r\ncoronavirus 2 (SARS-CoV-2) epidemic evolution would be extremely useful to\r\nsupport authorities in designing healthcare policies and lockdown measures to\r\ncontain its impact on public health and economy. In Italy, the devised forecasts\r\nhave been mostly based on a pure data-driven approach, by fitting and\r\nextrapolating open data on the epidemic evolution collected by the Italian Civil\r\nProtection Center. In this respect, SIR epidemiological models, which start from the\r\ndescription of the nonlinear interactions between population compartments,\r\nwould be a much more desirable approach to understand and predict the collective\r\nemergent response. The present contribution addresses the fundamental question\r\nwhether a SIR epidemiological model, suitably enriched with asymptomatic and\r\ndead individual compartments, could be able to provide reliable predictions on the\r\nepidemic evolution. To this aim, a machine learning approach based on particle\r\nswarm optimization (PSO) is proposed to automatically identify the model\r\nparameters based on a training set of data of progressive increasing size,\r\nconsidering Lombardy in Italy as a case study. The analysis of the scatter in the\r\nforecasts shows that model predictions are quite sensitive to the size of the dataset\r\nused for training, and that further data are still required to achieve convergent -\r\nand therefore reliable- predictions."^^ . "2020-04-16" . . "11" . . "IMT School for Advanced Studies Lucca"^^ . . . . . . . "Marco"^^ . "Paggi"^^ . "Marco Paggi"^^ . . . . . . "Simulation of Covid-19 epidemic evolution:\r\nare compartmental models really predictive? (PDF)"^^ . . . . . . "TR_11_2020_Paggi.pdf"^^ . . "HTML Summary of #4076 \n\nSimulation of Covid-19 epidemic evolution: \nare compartmental models really predictive?\n\n" . "text/html" . . . "HA Statistics"@en . . . "TJ Mechanical engineering and machinery"@en . .