Mostrar el registro sencillo del ítem

dc.contributor.authorRodriguez-Leon, C.
dc.contributor.authorArevalo, William
dc.contributor.authorBanos, Oresti
dc.contributor.authorVillalonga, Claudia
dc.date2021
dc.date.accessioned2022-03-18T11:56:19Z
dc.date.available2022-03-18T11:56:19Z
dc.identifier.isbn9783030850296
dc.identifier.issn0302-9743
dc.identifier.urihttps://reunir.unir.net/handle/123456789/12682
dc.description.abstractDiabetic retinopathy is a complication of diabetes mellitus. Its early diagnosis can prevent its progression and avoid the development of other major complications such as blindness. Deep learning and transfer learning appear in this context as powerful tools to aid in diagnosing this condition. The present work proposes to experiment with different models of pre-trained convolutional neural networks to determine which one fits best the problem of predicting diabetic retinopathy. The Diabetic Retinopathy Detection dataset supported by the EyePACS competition is used for evaluation. Seven pre-trained CNN models implemented in the Keras library developed in Python and, in this case, executed in the Kaggle platform, are used. Results show that no architecture performs better in all evaluation metrics. From a balanced behaviour perspective, the MobileNetV2 model stands out, with execution times almost half that of the slowest CNNs and without falling into overfitting with 20 learning epochs. InceptionResNetV2 stands out from the perspective of best performance, with a Kappa coefficient of 0.7588.es_ES
dc.language.isoenges_ES
dc.publisherSpringer Science and Business Media Deutschland GmbHes_ES
dc.relation.ispartofseries;vol. 12861
dc.relation.urihttps://link.springer.com/chapter/10.1007/978-3-030-85030-2_44es_ES
dc.rightsrestrictedAccesses_ES
dc.subjectdeep learninges_ES
dc.subjectdiabetic retinopathyes_ES
dc.subjecttransfer learninges_ES
dc.subjectScopus(2)es_ES
dc.subjectWOS(2)es_ES
dc.titleDeep Learning for Diabetic Retinopathy Predictiones_ES
dc.typeconferenceObjectes_ES
reunir.tag~ARIes_ES
dc.identifier.doihttps://doi.org/10.1007/978-3-030-85030-2_44


Ficheros en el ítem

FicherosTamañoFormatoVer

No hay ficheros asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem