Počet záznamů: 1
Mixture ratio modeling of dynamic systems
- 1.
SYSNO ASEP 0539397 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název Mixture ratio modeling of dynamic systems Tvůrce(i) Kárný, Miroslav (UTIA-B) RID, ORCID
Ruman, Marko (UTIA-B)Celkový počet autorů 2 Zdroj.dok. International Journal of Adaptive Control and Signal Processing. - : Wiley - ISSN 0890-6327
Roč. 35, č. 5 (2021), s. 660-675Poč.str. 16 s. Forma vydání Online - E Jazyk dok. eng - angličtina Země vyd. GB - Velká Británie Klíč. slova approximate Bayesian estimation ; black-box dynamic model ; data stream processing ; universal approximation ; mixture model ; Kullback-Leibler divergence Vědní obor RIV BB - Aplikovaná statistika, operační výzkum Obor OECD Automation and control systems CEP LTC18075 GA MŠMT - Ministerstvo školství, mládeže a tělovýchovy Způsob publikování Omezený přístup Institucionální podpora UTIA-B - RVO:67985556 UT WOS 000616106100001 EID SCOPUS 85100778905 DOI 10.1002/acs.3219 Anotace Any knowledge extraction relies (possibly implicitly) on a hypothesis about the modelled-data dependence. The extracted knowledge ultimately serves to a decision-making (DM). DM always faces uncertainty and this makes probabilistic modelling adequate. The inspected black-box modeling deals with “universal” approximators of the relevant probabilistic model. Finite mixtures with components in the exponential family are often exploited. Their attractiveness stems from their flexibility, the cluster interpretability of components and the existence of algorithms for processing high-dimensional data streams. They are even used in dynamic cases with mutually dependent data records while regression and auto-regression mixture components serve to the dependence modeling. These dynamic models, however, mostly assume data-independent component weights, that is, memoryless transitions between dynamic mixture components. Such mixtures are not universal approximators of dynamic probabilistic models. Formally, this follows from the fact that the set of finite probabilistic mixtures is not closed with respect to the conditioning, which is the key estimation and predictive operation. The paper overcomes this drawback by using ratios of finite mixtures as universally approximating dynamic parametric models. The paper motivates them, elaborates their approximate Bayesian recursive estimation and reveals their application potential. Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2022 Elektronická adresa https://onlinelibrary.wiley.com/doi/full/10.1002/acs.3219
Počet záznamů: 1