Hybridization of neural network models for the prediction of extreme significant wave height segments

Áreas de investigación:

• Methodology - Machine learning

Año:

2016

Tipo de publicación:

Artículo en conferencia

Autores:

• Durán-Rosal, Antonio Manuel
• Fernández, Juan Carlos
• Gutiérrez, Pedro Antonio
• Hervás-Martínez, César

Título del libro:

2016 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2016)

Páginas:

1-8

Organización:

Athens, Greece

Mes:

6th-9th December

ISBN:

978-1-5090-4240-1

BibTex:

@conference{timeDuranSSCI2016, author = "Antonio Manuel Dur{\'a}n-Rosal and Juan Carlos Fern{\'a}ndez and Pedro Antonio Guti{\'e}rrez and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "This work proposes a hybrid methodology for the detection and prediction of Extreme Significant Wave Height (ESWH) periods in oceans. In a first step, wave height time series is approximated by a labeled sequence of segments, which is obtained using a genetic algorithm in combination with a likelihood-based segmentation (GA+LS). Then, an artificial neural network classifier with hybrid basis functions is trained with a multiobjetive evolutionary algorithm (MOEA) in order to predict the occurrence of future ESWH segments based on past values. The methodology is applied to a buoy at the Gulf of Alaska and another one at Puerto Rico. The results show that the GA+LS is able to segment and group the ESWH values, and the neural network models, obtained by the MOEA, make good predictions maintaining a balance between global accuracy and minimum sensitivity for the detection of ESWH events. Moreover, hybrid neural networks are shown to lead to better results than pure models.", booktitle = "2016 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2016)", doi = "10.1109/SSCI.2016.7850144", isbn = "978-1-5090-4240-1", month = "6th-9th December", organization = " Athens, Greece", pages = "1--8", publisher = "IEEE Press", title = "{H}ybridization of neural network models for the prediction of extreme significant wave height segments", url = "dx.doi.org/10.1109/SSCI.2016.7850144", year = "2016", }

Abstract:

This work proposes a hybrid methodology for the detection and prediction of Extreme Significant Wave Height (ESWH) periods in oceans. In a first step, wave height time series is approximated by a labeled sequence of segments, which is obtained using a genetic algorithm in combination with a likelihood-based segmentation (GA+LS). Then, an artificial neural network classifier with hybrid basis functions is trained with a multiobjetive evolutionary algorithm (MOEA) in order to predict the occurrence of future ESWH segments based on past values. The methodology is applied to a buoy at the Gulf of Alaska and another one at Puerto Rico. The results show that the GA+LS is able to segment and group the ESWH values, and the neural network models, obtained by the MOEA, make good predictions maintaining a balance between global accuracy and minimum sensitivity for the detection of ESWH events. Moreover, hybrid neural networks are shown to lead to better results than pure models.