Weighted Cross-Entropy for Unbalanced Data with Application on COVID X-ray images

Basit Öğe Kaydı
dc.authorscopusid57220962785
dc.authorscopusid36782998200
dc.contributor.authorOzdemir, O.
dc.contributor.authorSonmez, E.B.
dc.date.accessioned2024-07-18T20:17:02Z
dc.date.available2024-07-18T20:17:02Z
dc.date.issued2020
dc.description2020 Innovations in Intelligent Systems and Applications Conference, ASYU 2020 -- 15 October 2020 through 17 October 2020 -- -- 165305en_US
dc.description.abstractSince December 2019 the world is infected by COVID-19 or Coronavirus disease, which spreads very quickly, out of control. The high number of precautions for laboratory access, which need to be taken to contain the virus, together with the difficulties in running the gold standard test for COVID-19, result in a practical incapability to make early diagnosis. Recent advances in deep learning algorithms allow efficient implementation of computer-aided diagnosis. This paper investigates on the performance of a very well known residual network, ResNet50, and a lightweight Atrous CNN (ACNN) network using a Weighted Cross-entropy (WCE) loss function, to alleviate imbalance on COVID datasets. As a result, ResNet50 model initialized with pre-trained weights fine-tuned by ImageNet dataset and exploiting WCE achieved the state-of-the-art performance on COVIDXRay-5K test set, with a top balanced accuracy of 99.87%. © 2020 IEEE.en_US
dc.identifier.doi10.1109/ASYU50717.2020.9259848
dc.identifier.isbn9781728191362
dc.identifier.scopus2-s2.0-85097935856en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://doi.org/10.1109/ASYU50717.2020.9259848
dc.identifier.urihttps://hdl.handle.net/11411/6385
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofProceedings - 2020 Innovations in Intelligent Systems and Applications Conference, ASYU 2020en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectAutomatic Diagnosisen_US
dc.subjectClassificationen_US
dc.subjectCoronavirusen_US
dc.subjectCovıd-19en_US
dc.subjectDeep Learningen_US
dc.subjectLoss Functionsen_US
dc.subjectWeighted Cross-Entropyen_US
dc.subjectComputer Aided İnstructionen_US
dc.subjectDeep Learningen_US
dc.subjectDisease Controlen_US
dc.subjectEntropyen_US
dc.subjectIntelligent Systemsen_US
dc.subjectLearning Algorithmsen_US
dc.subjectStatistical Testsen_US
dc.subjectCross Entropyen_US
dc.subjectEarly Diagnosisen_US
dc.subjectEfficient İmplementationen_US
dc.subjectGold Standardsen_US
dc.subjectLoss Functionsen_US
dc.subjectOut-Of-Controlen_US
dc.subjectState-Of-The-Art Performanceen_US
dc.subjectUnbalanced Dataen_US
dc.subjectComputer Aided Diagnosisen_US
dc.titleWeighted Cross-Entropy for Unbalanced Data with Application on COVID X-ray images
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus Indexed Publications