Modeling Beach Rotation Using a Novel Legendre Polynomial Feedforward Neural Network Trained by Nonlinear Constrained Optimization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Modeling Beach Rotation Using a Novel Legendre Polynomial Feedforward Neural Network Trained by Nonlinear Constrained Optimization

Anastasios Rigos
  • Fonction : Auteur
  • PersonId : 992525
George E. Tsekouras
  • Fonction : Auteur
  • PersonId : 992529
Antonios Chatzipavlis
  • Fonction : Auteur
  • PersonId : 1011995
Adonis F. Velegrakis
  • Fonction : Auteur
  • PersonId : 1011996

Résumé

A Legendre polynomial feedforward neural network is proposed to model/predict beach rotation. The study area is the reef-fronted Ammoudara beach, located at the northern coastline of Crete Island (Greece). Specialized experimental devices were deployed to generate a set of input-output data concerning the inshore bathymetry, the wave conditions and the shoreline position. The presence of the fronting beachrock reef (parallel to the shoreline) increases complexity and imposes high non-linear effects. The use of Legendre polynomials enables the network to capture data non-linearities. However, in order to maintain specific functional requirements, the connection weights must be confined within a pre-determined domain of values; it turns out that the network’s training process constitutes a constrained nonlinear programming problem, solved by the barrier method. The performance of the network is compared to other two neural-based approaches. Simulations show that the proposed network achieves a superior performance, which could be improved if an additional wave parameter (wave direction) was to be included in the input variables.
Fichier principal
Vignette du fichier
430537_1_En_15_Chapter.pdf (269.21 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01557619 , version 1 (06-07-2017)

Licence

Paternité

Identifiants

Citer

Anastasios Rigos, George E. Tsekouras, Antonios Chatzipavlis, Adonis F. Velegrakis. Modeling Beach Rotation Using a Novel Legendre Polynomial Feedforward Neural Network Trained by Nonlinear Constrained Optimization. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. pp.167-179, ⟨10.1007/978-3-319-44944-9_15⟩. ⟨hal-01557619⟩
71 Consultations
194 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More