Articolo in rivista, 2022, ENG, 10.1155/2022/9518303
Murari A.; Lungaroni M.; Rossi R.; Spolladore L.; Gelfusa M.
CNR ISTP - Istituto per la Scienza e Tecnologia dei Plasmi, Sede di Padova, Italy; Consorzio RFX (CNR, ENEA, INFN, Universita' di Padova, Acciaierie Venete SpA), Padova, Italy; University of Rome Tor Vergata, Department of Industrial Engineering, Roma, Italy.
It can be argued that the identification of sound mathematical models is the ultimate goal of any scientific endeavour. On the other hand, particularly in the investigation of complex systems and nonlinear phenomena, discriminating between alternative models can be a very challenging task. Quite sophisticated model selection criteria are available but their deployment in practice can be problematic. In this work, the Akaike Information Criterion is reformulated with the help of purely information theoretic quantities, namely, the Gibbs-Shannon entropy and the Mutual Information. Systematic numerical tests have proven the improved performances of the proposed upgrades, including increased robustness against noise and the presence of outliers. The same modifications can be implemented to rewrite also Bayesian statistical criteria, such as the Schwartz indicator, in terms of information-theoretic quantities, proving the generality of the approach and the validity of the underlying assumptions.
Complexity (Online) , pp. 9518303-1–9518303-12
Analysis of Experimental Data, Data-Driven Methods
ID: 470231
Year: 2022
Type: Articolo in rivista
Creation: 2022-08-30 10:26:19.000
Last update: 2022-11-28 22:33:35.000
CNR authors
CNR institutes
External links
OAI-PMH: Dublin Core
OAI-PMH: Mods
OAI-PMH: RDF
DOI: 10.1155/2022/9518303
URL: https://www.hindawi.com/journals/complexity/2022/9518303/
External IDs
CNR OAI-PMH: oai:it.cnr:prodotti:470231
DOI: 10.1155/2022/9518303
ISI Web of Science (WOS): 000850186500002
Scopus: 2-s2.0-85137711514