INCREMENTAL LOCALLY LINEAR FUZZY MODELING (Q4950601)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1428262
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | INCREMENTAL LOCALLY LINEAR FUZZY MODELING |
scientific article; zbMATH DE number 1428262 |
Statements
INCREMENTAL LOCALLY LINEAR FUZZY MODELING (English)
0 references
9 March 2001
0 references
fuzzy modeling
0 references
locally linear mappings
0 references
incremental modeling
0 references
fuzzy identification
0 references
clustering
0 references
triangular partitioning
0 references
0.87255466
0 references
0.8515557
0 references
0 references
0.8334425
0 references
The authors discuss an approach to modeling which consists of building fuzzy system models from data collected incrementally from real physical systems. A clustering method is used to filter out noise. Linearity in the output domain allows to build fuzzy models consisting of a reduced number of rules. Additional fuzzy rules would burden the system without improving its accuracy. From this approach results a triangular partitioning of the input space instead of the usual rectangular covering which would need much more rules in order to obtain the same accuracy.
0 references
