Mostrar el registro sencillo del ítem

dc.contributor.authorHernández Vasquez, Marco A
dc.contributor.authorFuentes Fino, Ricardo Javier
dc.contributor.authorCalderón-Ramírez, Saúl
dc.contributor.authorDomínguez-Merino, Enrique 
dc.contributor.authorLópez-Rubio, Ezequiel 
dc.contributor.authorMolina-Cabello, Miguel Angel
dc.date.accessioned2022-06-24T07:22:50Z
dc.date.available2022-06-24T07:22:50Z
dc.date.created2022-06-24
dc.date.issued2022
dc.identifier.urihttps://hdl.handle.net/10630/24482
dc.description.abstractLabeled medical datasets may include a limited number of observations for each class, while unlabeled datasets may include observations from patients with pathologies other than those observed in the labeled dataset. This negatively influences the performance of the prediction algorithms. Including out-of-distribution data in the unlabeled dataset can lead to varying degrees of performance degradation, or even improvement, by using a distance to measure how out-of-distribution a piece of data is. This work aims to propose an approach that allows estimating the predictive uncertainty of supervised algorithms, improving the behaviour when atypical samples are presented to the distribution of the dataset. In particular, we have used this approach to mammograms X-ray images applied to binary classification tasks. The proposal makes use of Feature Density, which consists of estimating the density of features from the calculation of a histogram. The obtained results report slight differences when different neural network architectures and uncertainty estimators are usedes_ES
dc.description.sponsorshipUniversidad de Málaga. Campus de Excelencia Internacional Andalucía Teches_ES
dc.language.isoenges_ES
dc.rightsinfo:eu-repo/semantics/openAccesses_ES
dc.subjectDensidades_ES
dc.subjectMétodos estadísticoses_ES
dc.subjectComputación hetereogéneaes_ES
dc.subjectMedidas de probabilidadeses_ES
dc.subjectLógicaes_ES
dc.subjectInteligencia artificiales_ES
dc.subjectBioinformáticaes_ES
dc.subjectIngeniería biomédicaes_ES
dc.subject.otherFeature Densityes_ES
dc.subject.otherMahalanobis distancees_ES
dc.subject.otherJensen-Shannon distancees_ES
dc.subject.otherUncertaintyes_ES
dc.subject.otherDeep Learninges_ES
dc.titleFeature density as an uncertainty estimator method in the binary classification mammography images task for a supervised deep learning modeles_ES
dc.typeinfo:eu-repo/semantics/conferenceObjectes_ES
dc.centroE.T.S.I. Informáticaes_ES
dc.relation.eventtitleInternational Work-Conference on Bioinformatics and Biomedical Engineeringes_ES
dc.relation.eventplaceGran Canarias, Españaes_ES
dc.relation.eventdateJunio 2022es_ES


Ficheros en el ítem

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

Mostrar el registro sencillo del ítem