Cascading and Ensemble Techniques in Deep Learning

In this study, we explore the integration of cascading and ensemble techniques in Deep Learning (DL) to improve prediction accuracy on diabetes data. The primary approach involves creating multiple Neural Networks (NNs), each predicting the outcome independently, and then feeding these initial predi...

Descripción completa

Detalles Bibliográficos
Autores: de Zarzà i Cubero, I., de Curtò y DíAz, J., Hernández-Orallo, Enrique, Calafate, Carlos
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/149186
Acceso en línea:http://hdl.handle.net/10609/149186
https://doi.org/10.3390/electronics12153354
Access Level:acceso abierto
Palabra clave:neural networks
cascading
ensemble
diabetes
id ES_b6086a9b8ebfc59272f0e5fae30b281a
oai_identifier_str oai:openaccess.uoc.edu:10609/149186
network_acronym_str ES
network_name_str España
repository_id_str
spelling Cascading and Ensemble Techniques in Deep Learningde Zarzà i Cubero, I.de Curtò y DíAz, J.Hernández-Orallo, EnriqueCalafate, Carlosneural networkscascadingensemblediabetesIn this study, we explore the integration of cascading and ensemble techniques in Deep Learning (DL) to improve prediction accuracy on diabetes data. The primary approach involves creating multiple Neural Networks (NNs), each predicting the outcome independently, and then feeding these initial predictions into another set of NN. Our exploration starts from an initial pre- liminary study and extends to various ensemble techniques including bagging, stacking, and finally cascading. The cascading ensemble involves training a second layer of models on the predictions of the first. This cascading structure, combined with ensemble voting for the final prediction, aims to exploit the strengths of multiple models while mitigating their individual weaknesses. Our results demonstrate significant improvement in prediction accuracy, providing a compelling case for the potential utility of these techniques in healthcare applications, specifically for prediction of diabetes where we achieve compelling model accuracy of 91.5% on the test set on a particular challenging dataset, where we compare thoroughly against many other methodologies.MDPI202320232023info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10609/149186https://doi.org/10.3390/electronics12153354reponame:O2, repositorio institucional de la UOCinstname:Universitat Oberta de Catalunya (UOC)InglésElectronics, 2023, 12(15), 1-18.https://doi.org/10.3390/electronics12153354CC BYhttp://creativecommons.org/licenses/by/4.0/es/info:eu-repo/semantics/openAccessoai:openaccess.uoc.edu:10609/1491862026-05-28T12:42:01Z
dc.title.none.fl_str_mv Cascading and Ensemble Techniques in Deep Learning
title Cascading and Ensemble Techniques in Deep Learning
spellingShingle Cascading and Ensemble Techniques in Deep Learning
de Zarzà i Cubero, I.
neural networks
cascading
ensemble
diabetes
title_short Cascading and Ensemble Techniques in Deep Learning
title_full Cascading and Ensemble Techniques in Deep Learning
title_fullStr Cascading and Ensemble Techniques in Deep Learning
title_full_unstemmed Cascading and Ensemble Techniques in Deep Learning
title_sort Cascading and Ensemble Techniques in Deep Learning
dc.creator.none.fl_str_mv de Zarzà i Cubero, I.
de Curtò y DíAz, J.
Hernández-Orallo, Enrique
Calafate, Carlos
author de Zarzà i Cubero, I.
author_facet de Zarzà i Cubero, I.
de Curtò y DíAz, J.
Hernández-Orallo, Enrique
Calafate, Carlos
author_role author
author2 de Curtò y DíAz, J.
Hernández-Orallo, Enrique
Calafate, Carlos
author2_role author
author
author
dc.subject.none.fl_str_mv neural networks
cascading
ensemble
diabetes
topic neural networks
cascading
ensemble
diabetes
description In this study, we explore the integration of cascading and ensemble techniques in Deep Learning (DL) to improve prediction accuracy on diabetes data. The primary approach involves creating multiple Neural Networks (NNs), each predicting the outcome independently, and then feeding these initial predictions into another set of NN. Our exploration starts from an initial pre- liminary study and extends to various ensemble techniques including bagging, stacking, and finally cascading. The cascading ensemble involves training a second layer of models on the predictions of the first. This cascading structure, combined with ensemble voting for the final prediction, aims to exploit the strengths of multiple models while mitigating their individual weaknesses. Our results demonstrate significant improvement in prediction accuracy, providing a compelling case for the potential utility of these techniques in healthcare applications, specifically for prediction of diabetes where we achieve compelling model accuracy of 91.5% on the test set on a particular challenging dataset, where we compare thoroughly against many other methodologies.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10609/149186
https://doi.org/10.3390/electronics12153354
url http://hdl.handle.net/10609/149186
https://doi.org/10.3390/electronics12153354
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Electronics, 2023, 12(15), 1-18.
https://doi.org/10.3390/electronics12153354
dc.rights.none.fl_str_mv CC BY
http://creativecommons.org/licenses/by/4.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv CC BY
http://creativecommons.org/licenses/by/4.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:O2, repositorio institucional de la UOC
instname:Universitat Oberta de Catalunya (UOC)
instname_str Universitat Oberta de Catalunya (UOC)
reponame_str O2, repositorio institucional de la UOC
collection O2, repositorio institucional de la UOC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417412728717312
score 15,301629

Similares en LA Referencia