|
|
|
|
|
|
|
Abstract
Interval-valued Type 2 fuzziness exists and provides a richer knowledge
representation and approximate reasoning for computing with words. First, it
has been shown that membership values reveal a scatter plot and thus
represents a varying degrees of meaning for words. This is realized whether
they are acquired subjectively in measurement experiments or they are
captured by fuzzy clustering methods. Secondly, it has been shown that the
combination of linguistic values with linguistic operators, such as, "AND",
"OR", "IMP", etc., as opposed to t-norms and co-norms, and standard
negation, generates Fuzzy Disjunctive and Conjunctive Canonical Forms, FDCF
and FCCF, respectively. Recently, we have shown that there is a natural
connection between Dempster's multi-valued mapping and interval-valued Type
2 fuzzy sets. In particular, it is shown that FDCF and FCCF corresponds to
lower and upper set approximations obtained by a newly proposed
Dempster-Turksen formalism.
Duration 1 hour