Hybridization of neural network models for the prediction of Extreme Significant Wave Height segments

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.

[1]  Sancho Salcedo-Sanz,et al.  Significant wave height estimation using SVR algorithms and shadowing information from simulated and real measured X-band radar images of the sea surface , 2015 .

[2]  Wlodzislaw Duch,et al.  Transfer functions: hidden possibilities for better neural networks , 2001, ESANN.

[3]  Shian-Jiann Lin,et al.  Ocean Warming Effect on Surface Gravity Wave Climate Change for the End of the Twenty-First Century , 2013 .

[4]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[5]  Wataru Kioka,et al.  An Extended Poisson test for Detecting the Difference Between the Past and Future Rates of Extremes of Sea wave Heights , 2015 .

[6]  Margaret J. Yelland,et al.  Changes in significant and maximum wave heights in the Norwegian Sea , 2014 .

[7]  Olatz Arbelaitz,et al.  An extensive comparative study of cluster validity indices , 2013, Pattern Recognit..

[8]  G. S. Dwarakish,et al.  Wave Prediction Using Neural Networks at New Mangalore Port along West Coast of India , 2015 .

[9]  Norbert Jankowski,et al.  Survey of Neural Transfer Functions , 1999 .

[10]  R. Lippmann.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[11]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[12]  R. Tibshirani,et al.  Generalized Additive Models , 1986 .

[13]  Tom Andersen,et al.  Can the Rayleigh distribution be used to determine extreme wave heights in non-breaking swell conditions? , 2016 .

[14]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[15]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[16]  Pedro Antonio Gutiérrez,et al.  Sensitivity Versus Accuracy in Multiclass Problems Using Memetic Pareto Evolutionary Neural Networks , 2010, IEEE Transactions on Neural Networks.

[17]  Wlodzislaw Duch,et al.  Constructive density estimation network based on several different separable transfer functions , 2001, ESANN.

[18]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[19]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[20]  David E. Rumelhart,et al.  Product Units: A Computationally Powerful and Biologically Plausible Extension to Backpropagation Networks , 1989, Neural Computation.

[21]  C. Guedes Soares,et al.  Regression quantile models for estimating trends in extreme significant wave heights , 2016 .

[22]  Nathan Intrator,et al.  A Hybrid Projection Based and Radial Basis Function Architecture , 2000, Multiple Classifier Systems.

[23]  Abdüsselam Altunkaynak,et al.  Prediction of significant wave height using spatial function , 2015 .

[24]  I. Johnstone,et al.  Projection-Based Approximation and a Duality with Kernel Methods , 1989 .

[25]  Pedro Antonio Gutiérrez,et al.  Applying a Hybrid Algorithm to the Segmentation of the Spanish Stock Market Index Time Series , 2015, IWANN.

[26]  J. Friedman,et al.  Projection Pursuit Regression , 1981 .

[27]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[28]  Oleg Makarynskyy,et al.  Wave Prediction and Data Supplementation with Artificial Neural Networks , 2007 .

[29]  Pedro Antonio Gutiérrez,et al.  Combined projection and kernel basis functions for classification in evolutionary neural networks , 2009, Neurocomputing.

[30]  A. C. Martínez-Estudillo,et al.  Hybridization of evolutionary algorithms and local search by means of a clustering method , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[31]  Charles Gide,et al.  Cours d'économie politique , 1911 .

[32]  Iulian B. Ciocoiu.  Hybrid Feedforward Neural Networks for Solving Classification Problems , 2004, Neural Processing Letters.