Morphological classification of microtidal sand and gravel beaches
Empreu sempre aquest identificador per citar o enllaçar aquest ítem
http://hdl.handle.net/10045/53513
Títol: | Morphological classification of microtidal sand and gravel beaches |
---|---|
Autors: | López, Isabel | Aragonés, Luis | Villacampa, Yolanda | Compañ, Patricia | Satorre Cuerda, Rosana |
Grups d'investigació o GITE: | Ingeniería del Terreno y sus Estructuras (InTerEs) | Modelización Matemática de Sistemas | Informática Industrial e Inteligencia Artificial |
Centre, Departament o Servei: | Universidad de Alicante. Departamento de Ingeniería Civil | Universidad de Alicante. Departamento de Matemática Aplicada | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Paraules clau: | Beaches classification | Artificial neural networks | SVM method | Posidonia oceanica |
Àrees de coneixement: | Ingeniería e Infraestructura de los Transportes | Matemática Aplicada | Ciencia de la Computación e Inteligencia Artificial |
Data de publicació: | 15-de novembre-2015 |
Editor: | Elsevier |
Citació bibliogràfica: | Ocean Engineering. 2015, 109: 309-319. doi:10.1016/j.oceaneng.2015.09.021 |
Resum: | A new classification of microtidal sand and gravel beaches with very different morphologies is presented below. In 557 studied transects, 14 variables were used. Among the variables to be emphasized is the depth of the Posidonia oceanica. The classification was performed for 9 types of beaches: Type 1: Sand and gravel beaches, Type 2: Sand and gravel separated beaches, Type 3: Gravel and sand beaches, Type 4: Gravel and sand separated beaches, Type 5: Pure gravel beaches, Type 6: Open sand beaches, Type 7: Supported sand beaches, Type 8: Bisupported sand beaches and Type 9: Enclosed beaches. For the classification, several tools were used: discriminant analysis, neural networks and Support Vector Machines (SVM), the results were then compared. As there is no theory for deciding which is the most convenient neural network architecture to deal with a particular data set, an experimental study was performed with different numbers of neuron in the hidden layer. Finally, an architecture with 30 neurons was chosen. Different kernels were employed for SVM (Linear, Polynomial, Radial basis function and Sigmoid). The results obtained for the discriminant analysis were not as good as those obtained for the other two methods (ANN and SVM) which showed similar success. |
URI: | http://hdl.handle.net/10045/53513 |
ISSN: | 0029-8018 (Print) | 1873-5258 (Online) |
DOI: | 10.1016/j.oceaneng.2015.09.021 |
Idioma: | eng |
Tipus: | info:eu-repo/semantics/article |
Drets: | © 2015 Elsevier Ltd. |
Revisió científica: | si |
Versió de l'editor: | http://dx.doi.org/10.1016/j.oceaneng.2015.09.021 |
Apareix a la col·lecció: | INV - i3a - Artículos de Revistas INV - INTERES - Artículos de Revistas INV - MMS - Artículos de Revistas INV - AORTA - Artículos de Revistas INV - Smart Learning - Artículos de Revistas |
Arxius per aquest ítem:
Arxiu | Descripció | Tamany | Format | |
---|---|---|---|---|
2015_Lopez_etal_OceanEng_final.pdf | Versión final (acceso restringido) | 7,25 MB | Adobe PDF | Obrir Sol·licitar una còpia |
Tots els documents dipositats a RUA estan protegits per drets d'autors. Alguns drets reservats.