Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting

<p>Accurate control of wave energy devices relies heavily on precise forecasts of wave heights, yet the dynamic and fluctuating nature of historical wave data presents significant challenges to achieving this precision. Neural networks help address this issue by extracting meaningful patterns...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Aryan Bhambu (18767731) (author)
مؤلفون آخرون: Ruobin Gao (16003195) (author), Ponnuthurai Nagaratnam Suganthan (11274636) (author), Natarajan Selvaraju (22631420) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513532710617088
author Aryan Bhambu (18767731)
author2 Ruobin Gao (16003195)
Ponnuthurai Nagaratnam Suganthan (11274636)
Natarajan Selvaraju (22631420)
author2_role author
author
author
author_facet Aryan Bhambu (18767731)
Ruobin Gao (16003195)
Ponnuthurai Nagaratnam Suganthan (11274636)
Natarajan Selvaraju (22631420)
author_role author
dc.creator.none.fl_str_mv Aryan Bhambu (18767731)
Ruobin Gao (16003195)
Ponnuthurai Nagaratnam Suganthan (11274636)
Natarajan Selvaraju (22631420)
dc.date.none.fl_str_mv 2025-11-12T15:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.asoc.2025.114136
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Deep_random_vector_functional_link_transformer_network_with_multiple_output_layers_for_significant_wave_height_forecasting/30636416
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Artificial intelligence
Machine learning
Forecasting
Transformer
Multiple output layers
Time series
Deep ensemble random vector functional vector link
Deep neural networks
Ensemble learning
Randomized neural networks
dc.title.none.fl_str_mv Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Accurate control of wave energy devices relies heavily on precise forecasts of wave heights, yet the dynamic and fluctuating nature of historical wave data presents significant challenges to achieving this precision. Neural networks help address this issue by extracting meaningful patterns from past observations to improve wave height predictions. This paper introduces a novel random vector functional link transformer (RFT) and ensemble deep random vector functional link transformer (edRFT) networks to capture the dynamic characteristics of significant wave heights. The model employs hidden blocks based on transformer encoders to effectively capture complex sequential dependencies in the data. The proposed model incorporates randomly initialized and fixed weights for the hidden layers to ensure stability during training. Stacked hidden layers are incorporated to facilitate deep representation learning, allowing the extraction of complex patterns from the data. Forecasts are generated by integrating the outputs of each layer using an ensemble approach. The computational results demonstrate the superiority of the proposed models through a comparative analysis against state-of-the-art approaches across fifteen significant wave height time series, validated by three error metrics and a statistical test.</p><h2>Other Information</h2> <p> Published in: Applied Soft Computing<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.asoc.2025.114136" target="_blank">https://dx.doi.org/10.1016/j.asoc.2025.114136</a></p>
eu_rights_str_mv openAccess
id Manara2_afdb8bb85166b7c0318cb3b9a580bc71
identifier_str_mv 10.1016/j.asoc.2025.114136
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30636416
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Deep random vector functional link transformer network with multiple output layers for significant wave height forecastingAryan Bhambu (18767731)Ruobin Gao (16003195)Ponnuthurai Nagaratnam Suganthan (11274636)Natarajan Selvaraju (22631420)EngineeringElectronics, sensors and digital hardwareInformation and computing sciencesArtificial intelligenceMachine learningForecastingTransformerMultiple output layersTime seriesDeep ensemble random vector functional vector linkDeep neural networksEnsemble learningRandomized neural networks<p>Accurate control of wave energy devices relies heavily on precise forecasts of wave heights, yet the dynamic and fluctuating nature of historical wave data presents significant challenges to achieving this precision. Neural networks help address this issue by extracting meaningful patterns from past observations to improve wave height predictions. This paper introduces a novel random vector functional link transformer (RFT) and ensemble deep random vector functional link transformer (edRFT) networks to capture the dynamic characteristics of significant wave heights. The model employs hidden blocks based on transformer encoders to effectively capture complex sequential dependencies in the data. The proposed model incorporates randomly initialized and fixed weights for the hidden layers to ensure stability during training. Stacked hidden layers are incorporated to facilitate deep representation learning, allowing the extraction of complex patterns from the data. Forecasts are generated by integrating the outputs of each layer using an ensemble approach. The computational results demonstrate the superiority of the proposed models through a comparative analysis against state-of-the-art approaches across fifteen significant wave height time series, validated by three error metrics and a statistical test.</p><h2>Other Information</h2> <p> Published in: Applied Soft Computing<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.asoc.2025.114136" target="_blank">https://dx.doi.org/10.1016/j.asoc.2025.114136</a></p>2025-11-12T15:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.asoc.2025.114136https://figshare.com/articles/journal_contribution/Deep_random_vector_functional_link_transformer_network_with_multiple_output_layers_for_significant_wave_height_forecasting/30636416CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306364162025-11-12T15:00:00Z
spellingShingle Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
Aryan Bhambu (18767731)
Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Artificial intelligence
Machine learning
Forecasting
Transformer
Multiple output layers
Time series
Deep ensemble random vector functional vector link
Deep neural networks
Ensemble learning
Randomized neural networks
status_str publishedVersion
title Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
title_full Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
title_fullStr Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
title_full_unstemmed Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
title_short Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
title_sort Deep random vector functional link transformer network with multiple output layers for significant wave height forecasting
topic Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Artificial intelligence
Machine learning
Forecasting
Transformer
Multiple output layers
Time series
Deep ensemble random vector functional vector link
Deep neural networks
Ensemble learning
Randomized neural networks