Affiliations: [a] School of Computing, University of Portsmouth, Portsmouth, UK | [b] School of Engineering, University of Portsmouth, Portsmouth, UK | [c] Bulgarian Academy of Sciences, Institute of Information and Communication Technologies, Sofia, Bulgaria
Correspondence:
[*]
Corresponding author: Alexander Gegov, School of Computing, University of Portsmouth, Buckingham Building, Portsmouth PO1 3HE, UK. E-mail:[email protected]
Abstract: This paper proposes a complexity management methodology
for fuzzy systems with feedforward rule bases. The methodology is based on
formal methods for presentation, manipulation and transformation of fuzzy
rule bases. First, Boolean matrices are used for formal presentation of rule
bases. Then, binary merging operations are used for formal manipulation of
rule bases. Finally, repetitive merging operations are used for formal
transformation of rule bases. The formal methods facilitate the
understanding and modelling of fuzzy systems in terms of interacting
subsystems. In particular, the methods reduce the qualitative complexity in
fuzzy systems by improving the transparency of the rule bases.
