Hybridization of neural network models for the prediction of extreme significant wave height segments
Congress: 2016 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2016)
City: Athens (Greece)
Date: 6th-9th December
Year: 2016
Pages: 1 - 8
URL: https://ieeexplore.ieee.org/document/7850144Abstract
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 in the Gulf of Alaska and another one in 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.
Citation
@inproceedings{duran2016hybridization,
title={Hybridization of neural network models for the prediction of Extreme Significant Wave Height segments},
author={Dur{\'a}n-Rosal, Antonio M and Fern{\'a}ndez, Juan C and Guti{\'e}rrez, Pedro A and Herv{\'a}s-Mart{\'\i}nez, C{\'e}sar},
booktitle={2016 IEEE Symposium Series on Computational Intelligence (SSCI)},
pages={1--8},
year={2016},
organization={IEEE}
}