A
le
x
a
n
d
er K
a
rl
ss
o
n
E
va
lu
ati
ng C
re
da
l S
et T
he
or
y a
s a B
eli
ef F
ra
m
ew
or
k i
n H
ig
h-L
ev
el I
nf
or
m
ati
on F
us
io
n
2010 issn 1650-8580 isbn 978-91-7668-740-6Alexander Karlsson is a part of the information fusion
research program at the University of Skövde, Sweden. His main research interests are Bayesian theory and imprecise probability for managing uncertainty regarding some environment of interest.
In many applications, one wants to determine the true state of some aspect of an environment but fails because of various types of uncertainty. In such cases, it is neces-sary to interpret information regarding the environment as evidence that affects one’s belief for different possibilities of the true state. The problem of managing such belief and evidence is the main task of a belief framework. In this thesis, Karlsson explores whether credal set theory yields measurable advantages, compared to Bayesian theory, when used as a belief framework in high-level information fusion for automated decision-making, i.e., when decisions are made by some algorithm.
Örebro Studies in Technology 38 örebro 2010
Doctoral Dissertation
