Epidemic dynamics via wavelet theory and machine learning with applications to Covid-19

0536558 - MÚ 2021 RIV CH eng J - Journal Article
Tat Dat, T. - Frédéric, P. - Hang, N.T.T. - Jules, M. - Duc Thang, N. - Piffault, C. - Willy, R. - Susely, F. - Le, Hong-Van - Tuschmann, W. - Tien Zung, N.
Epidemic dynamics via wavelet theory and machine learning with applications to Covid-19.
Biology. Roč. 9, č. 12 (2020), č. článku 477. E-ISSN 2079-7737
R&D Projects: GA ČR(CZ) GC18-01953J
Institutional support: RVO:67985840
Keywords : epidemic-fitted wavelet * epidemic dynamics * model selection * Covid-19 spread predicting
OECD category: Pure mathematics
Impact factor: 5.079, year: 2020
Method of publishing: Open access
https://doi.org/10.3390/biology9120477

We introduce the concept of epidemic-fitted wavelets which comprise, in particular, as special cases the number I(t) of infectious individuals at time t in classical SIR models and their derivatives. We present a novel method for modelling epidemic dynamics by a model selection method using wavelet theory and, for its applications, machine learning-based curve fitting techniques. Our universal models are functions that are finite linear combinations of epidemic-fitted wavelets. We apply our method by modelling and forecasting, based on the Johns Hopkins University dataset, the spread of the current Covid-19 (SARS-CoV-2) epidemic in France, Germany, Italy and the Czech Republic, as well as in the US federal states New York and Florida.
Permanent Link: http://hdl.handle.net/11104/0314328