Output details
11 - Computer Science and Informatics
University of Manchester
Article title
An Evolving Construction Scheme for Fuzzy Systems
Type
D - Journal article
Title of journal
IEEE Transaction on Fuzzy Systems
Article number
-
Volume number
18
Issue number
4
First page of article
755
ISSN of journal
1063-6706
Year of publication
2010
URL
-
Number of additional authors
2
Additional information
<24> For a highly complex nonlinear system, finding a mathematical model which is accurate and interpretable simultaneously is a long standing unsolved problem in machine learning. This paper is significant because it proposed a fuzzy system approach and algorithm to find such a model effectively. By incrementally evolving the model structure till the best model accuracy is achieved, this approach shows advantages including: it identifies the structures and parameters of nonlinear fuzzy systems automatically with good accuracy; and the identified systems can be represented as interpretable and understandable linguistic rules.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
11
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-