0478074 20240103214519.120170919235959.9 85030092933 000419919900001 10.1002/acs.2821 13 s. P cav_un_epca*02567720890-6327321 (2018)1-12Wiley approximate filtering marginalized filters particle filtering cav_un_auth*0242543 Dedecius Kamil Adaptivní systémy Department of Adaptive Systems AS AS UTIA-B Department of Adaptive Systems CZ Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2017/AS/dedecius-0478074.pdf cav_un_auth*0331019 GA16-09848S GA ČR CZ The marginalized particle filtering (MPF) is a powerful technique reducing the number of particles necessary to effectively estimate hidden states of state-space models. This paper alleviates the assumption of a fully known and computationally tractable observation model. Exploiting the recent developments in the theory of approximate Bayesian computation (ABC) filtration, an ABC counterpart of MPF is proposed, applicable when the observation model is too complex to be evaluated analytically or even numerically, but it is still possible to sample from it by plugging in the state. The novelty is 2-fold. First, ABC methods have not been used in marginalized filtering yet. Second, a new multivariate robust method for evaluation of particle weights is proposed. The goal of this paper is to demonstrate the idea on the background of the MPF with a particular accent on exposition. BB 10000 10100 10103 2019 1 4 A hod 4ah 20231122142640.9 RVO:67985556 http://hdl.handle.net/11104/0274422 1 Department of Adaptive Systems UTIA-B 10200 COMPUTER SCIENCE, CYBERNETICS S 3+4 Article Automation Control Systems|Engineering Electrical Electronic AUTOMATION&CONTROLSYSTEMS|ENGINEERING.ELECTRICAL&ELECTRONIC 2.366 0.417 5.5 0.0039 0.655 2066 0.885 1.941 103 Q2 48.708 51.4 Q3 Q2 0.73 Q2 52.068 2018 Soubory v repozitáři: dedecius-0478074.pdf 85030092933 SCOPUS PUBMED 000419919900001 WOS cav_un_epca*0256772 International Journal of Adaptive Control and Signal Processing 0890-6327 1099-1115 Roč. 32 č. 1 2018 1 12 Wiley