Robust interval type-2 FCRM algorithm for nonlinear systems identification in a stochastic environment

This paper investigates the sensibility of the interval type-2 fuzzy c-regression algorithm to noise and outliers. To overcome this problem, a modified version of this algorithm is presented. The consequences parameters of local models are estimated using the weighted recursive least squares method....

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2017 International Conference on Control, Automation and Diagnosis (ICCAD) s. 180 - 184
Hlavní autoři:	Sameh, Khadhraoui, Chaari, Abdelkader
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 01.01.2017
Témata:	Algorithm design and analysis Clustering algorithms interval type-2 fuzzy c-regression models algorithm Linear programming Mathematical model Noise measurement noisy clustering algorithm outliers Partitioning algorithms Robustness Type-2 fuzzy sets weighted recursive least square
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	This paper investigates the sensibility of the interval type-2 fuzzy c-regression algorithm to noise and outliers. To overcome this problem, a modified version of this algorithm is presented. The consequences parameters of local models are estimated using the weighted recursive least squares method. This approach is tested and validated using two examples.
DOI:	10.1109/CADIAG.2017.8075653