๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Improving fuzzy systems identification with data transformations

โœ Scribed by Armin Shmilovici; Joseph Aguilar-Martin

Publisher
Elsevier Science
Year
1999
Tongue
English
Weight
293 KB
Volume
22
Category
Article
ISSN
0888-613X

No coin nor oath required. For personal study only.

โœฆ Synopsis

A practical problem in the identiยฎcation of fuzzy systems from data, is the design and the tuning of the membership functions. We demonstrate that if the data is properly transformed before the identiยฎcation process, the resulting fuzzy model can be improved to the point it may not need a further tuning. The signiยฎcance of the data transform can be validated using statistical methods. The method is demonstrated on a time series prediction problem, using the BoxยฑCox transform.

๐Ÿ“œ SIMILAR VOLUMES

Nonlinear system identification with lim
Nonlinear system identification with limited time data
โœ A.E. Pearson ๐Ÿ“‚ Article ๐Ÿ“… 1979 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 918 KB

A finite time interval parameter identification technique, which accommodates unknown analytical disturbances and avoids initial state estimation, is applicable to a class of nonlinear time varying systems.

Identification of dynamic process system
Identification of dynamic process systems with surrogate data methods
โœ Jakobus P. Barnard; Chris Aldrich; Marius Gerber ๐Ÿ“‚ Article ๐Ÿ“… 2001 ๐Ÿ› American Institute of Chemical Engineers ๐ŸŒ English โš– 627 KB

## Abstract Identifying the underlying dynamics of chemical process systems from experimental data is complicated, owing to a mixture of influences that cause erratic fluctuations in the time series. These influences can be notoriously difficult to disentangle. The development of process models is

Fuzzy system identification using an ada
Fuzzy system identification using an adaptive learning rule with terminal attractors
โœ Chuan-Kai Lin; Sheng-De Wang ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 573 KB

A fuzzy model with an adaptive learning rule is proposed to approximate a class of nonlinear systems. The proposed adaptive learning rule uses the concept of terminal attractors and guarantees that the identification is stable and fast convergence in finite time. Another subject of this paper is to