0464524 20240103212835.820161031235959.9 84988651944 000389706900017 10.1007/978-3-319-45559-4_17 10 s. P cav_un_epca*0464523978-3-642-29460-00302-97439861164-173SwitzerlandSpringer2016VejnarováJiřinaKratochvílVáclav IPFP belief function operator of composition cav_un_auth*0216188 Matematická teorie rozhodování Department of Decision Making Theory MTR MTR Department of Decision Making Theory 50 Kratochvíl Václav UTIA-B CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101223 Matematická teorie rozhodování Department of Decision Making Theory MTR MTR Department of Decision Making Theory 50 Vejnarová Jiřina UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2016/MTR/kratochvil-0464524.pdf cav_un_auth*0332303 GA16-12010S GA ČR CZ Iterative Proportional Fitting Procedure is commonly used in probability theory for construction of a joint probability distribution from a system of its marginals. A similar idea can be used in case of belief functions thanks to special operators of composition defined in this framework. In this paper, a formerly designed IPF procedure is further studied. We propose a modification of composition operator (for the purpose of the procedure), compare the behavior of the modified procedure with the previous one and prove its convergence. cav_un_auth*0334433 International Conference on Belief Functions 2016 /4./ 21.09.2016-23.09.2016 Prague CZ IN 2017 PR RVO:67985556 http://hdl.handle.net/11104/0263959 S 3+4 Proceedings Paper Computer Science Artificial Intelligence 0.325 Q2 Q2 2016 84988651944 SCOPUS 000389706900017 WOS cav_un_epca*0464523 Belief Functions: Theory and Applications 978-3-642-29460-0 0302-9743 164-173 164 173 Switzerland Springer 2016 Lecture Notes in Artificial Intelligence Subseries of Lecture Notes in Computer Science 9861 Vejnarová Jiřina 340 Kratochvíl Václav 340