Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

Ryad Zemouri; Daniel Racoceanu; Noureddine Zerhouni; Eugenia Minca; Florin Filip

doi:10.1063/1.3106518

Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

Ryad Zemouri, Daniel Racoceanu, Noureddine Zerhouni, Eugenia Minca, Florin Filip

Producción científica: Contribución a una revista › Artículo de la conferencia › revisión exhaustiva

4 Citas (Scopus)

Resumen

In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.

Idioma original	Inglés
Páginas (desde-hasta)	85-90
Número de páginas	6
Publicación	AIP Conference Proceedings
Volumen	1107
DOI	https://doi.org/10.1063/1.3106518
Estado	Publicada - 2009
Publicado de forma externa	Sí
Evento	2nd Mediterranean Conference on Intelligent Systems and Automation, CISA 2009 - Zarzis, Túnez Duración: 23 mar. 2009 → 25 mar. 2009

Acceder al documento

10.1063/1.3106518

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

@article{6a4b2a16b3034b7791fa342685e221f2,

title = "Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction",

abstract = "In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.",

keywords = "Fuzzy Min-Max technique, K-means algorithm, Network, Recurrent Network, Time Series Prediction",

author = "Ryad Zemouri and Daniel Racoceanu and Noureddine Zerhouni and Eugenia Minca and Florin Filip",

year = "2009",

doi = "10.1063/1.3106518",

language = "English",

volume = "1107",

pages = "85--90",

journal = "AIP Conference Proceedings",

issn = "0094-243X",

note = "2nd Mediterranean Conference on Intelligent Systems and Automation, CISA 2009 ; Conference date: 23-03-2009 Through 25-03-2009",

}

TY - JOUR

T1 - Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

AU - Zemouri, Ryad

AU - Racoceanu, Daniel

AU - Zerhouni, Noureddine

AU - Minca, Eugenia

AU - Filip, Florin

PY - 2009

Y1 - 2009

N2 - In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.

AB - In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.

KW - Fuzzy Min-Max technique

KW - K-means algorithm

KW - Network

KW - Recurrent Network

KW - Time Series Prediction

UR - https://www.scopus.com/pages/publications/65649099188

U2 - 10.1063/1.3106518

DO - 10.1063/1.3106518

M3 - Conference article

AN - SCOPUS:65649099188

SN - 0094-243X

VL - 1107

SP - 85

EP - 90

JO - AIP Conference Proceedings

JF - AIP Conference Proceedings

T2 - 2nd Mediterranean Conference on Intelligent Systems and Automation, CISA 2009

Y2 - 23 March 2009 through 25 March 2009

ER -

Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

Resumen

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto