Heave compensation prediction based on echo state network with correntropy induced loss function.

In this paper, a new prediction approach is proposed for ocean vessel heave compensation based on echo state network (ESN). To improve the prediction accuracy and enhance the robustness against noise and outliers, a generalized similarity measure called correntropy is introduced into ESN training, w...

Full description

Bibliographic Details
Main Authors: Xiaogang Huang, Dongge Lei, Lulu Cai, Tianhao Tang, Zhibin Wang
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2019-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0217361
id doaj-4d00923d470345aaa753fbedc8096df1
record_format Article
spelling doaj-4d00923d470345aaa753fbedc8096df12021-03-03T21:12:47ZengPublic Library of Science (PLoS)PLoS ONE1932-62032019-01-01146e021736110.1371/journal.pone.0217361Heave compensation prediction based on echo state network with correntropy induced loss function.Xiaogang HuangDongge LeiLulu CaiTianhao TangZhibin WangIn this paper, a new prediction approach is proposed for ocean vessel heave compensation based on echo state network (ESN). To improve the prediction accuracy and enhance the robustness against noise and outliers, a generalized similarity measure called correntropy is introduced into ESN training, which is referred as corr-ESN. An iterative method based on half-quadratic minimization is derived to train corr-ESN. The proposed corr-ESN is used for the heave motion prediction. The experimental results verify its effectiveness.https://doi.org/10.1371/journal.pone.0217361
collection DOAJ
language English
format Article
sources DOAJ
author Xiaogang Huang
Dongge Lei
Lulu Cai
Tianhao Tang
Zhibin Wang
spellingShingle Xiaogang Huang
Dongge Lei
Lulu Cai
Tianhao Tang
Zhibin Wang
Heave compensation prediction based on echo state network with correntropy induced loss function.
PLoS ONE
author_facet Xiaogang Huang
Dongge Lei
Lulu Cai
Tianhao Tang
Zhibin Wang
author_sort Xiaogang Huang
title Heave compensation prediction based on echo state network with correntropy induced loss function.
title_short Heave compensation prediction based on echo state network with correntropy induced loss function.
title_full Heave compensation prediction based on echo state network with correntropy induced loss function.
title_fullStr Heave compensation prediction based on echo state network with correntropy induced loss function.
title_full_unstemmed Heave compensation prediction based on echo state network with correntropy induced loss function.
title_sort heave compensation prediction based on echo state network with correntropy induced loss function.
publisher Public Library of Science (PLoS)
series PLoS ONE
issn 1932-6203
publishDate 2019-01-01
description In this paper, a new prediction approach is proposed for ocean vessel heave compensation based on echo state network (ESN). To improve the prediction accuracy and enhance the robustness against noise and outliers, a generalized similarity measure called correntropy is introduced into ESN training, which is referred as corr-ESN. An iterative method based on half-quadratic minimization is derived to train corr-ESN. The proposed corr-ESN is used for the heave motion prediction. The experimental results verify its effectiveness.
url https://doi.org/10.1371/journal.pone.0217361
work_keys_str_mv AT xiaoganghuang heavecompensationpredictionbasedonechostatenetworkwithcorrentropyinducedlossfunction
AT donggelei heavecompensationpredictionbasedonechostatenetworkwithcorrentropyinducedlossfunction
AT lulucai heavecompensationpredictionbasedonechostatenetworkwithcorrentropyinducedlossfunction
AT tianhaotang heavecompensationpredictionbasedonechostatenetworkwithcorrentropyinducedlossfunction
AT zhibinwang heavecompensationpredictionbasedonechostatenetworkwithcorrentropyinducedlossfunction
_version_ 1714818179910336512