Consequential Advancements of Self-Supervised Learning (SSL) in Deep Learning Contexts

Basit Öğe Kaydı
dc.authoridHameed, Alaa Ali/0000-0002-8514-9255
dc.authoridSyafrudin, Muhammad/0000-0002-5640-4413
dc.authoridFitriyani, Norma Latif/0000-0002-1133-3965
dc.authoridABDULRAZZAQ, Mohammed Majid/0000-0003-1850-9473
dc.authoridYon, Dong Keon/0000-0003-1628-9948
dc.authoridRAMAHA, NEHAD T.A/0000-0003-2600-4125
dc.authoridSalman, Mohammad/0000-0002-1769-6652
dc.authorwosidHameed, Alaa Ali/ABI-8417-2020
dc.authorwosidSyafrudin, Muhammad/P-9657-2017
dc.authorwosidFitriyani, Norma Latif/S-4105-2018
dc.authorwosidABDULRAZZAQ, Mohammed Majid/AEN-7926-2022
dc.authorwosidYon, Dong Keon/M-1264-2017
dc.contributor.authorAbdulrazzaq, Mohammed Majid
dc.contributor.authorRamaha, Nehad T. A.
dc.contributor.authorHameed, Alaa Ali
dc.contributor.authorSalman, Mohammad
dc.contributor.authorYon, Dong Keon
dc.contributor.authorFitriyani, Norma Latif
dc.contributor.authorSyafrudin, Muhammad
dc.date.accessioned2024-05-19T14:40:43Z
dc.date.available2024-05-19T14:40:43Z
dc.date.issued2024
dc.departmentİstinye Üniversitesien_US
dc.description.abstractSelf-supervised learning (SSL) is a potential deep learning (DL) technique that uses massive volumes of unlabeled data to train neural networks. SSL techniques have evolved in response to the poor classification performance of conventional and even modern machine learning (ML) and DL models of enormous unlabeled data produced periodically in different disciplines. However, the literature does not fully address SSL's practicalities and workabilities necessary for industrial engineering and medicine. Accordingly, this thorough review is administered to identify these prominent possibilities for prediction, focusing on industrial and medical fields. This extensive survey, with its pivotal outcomes, could support industrial engineers and medical personnel in efficiently predicting machinery faults and patients' ailments without referring to traditional numerical models that require massive computational budgets, time, storage, and effort for data annotation. Additionally, the review's numerous addressed ideas could encourage industry and healthcare actors to take SSL principles into an agile application to achieve precise maintenance prognostics and illness diagnosis with remarkable levels of accuracy and feasibility, simulating functional human thinking and cognition without compromising prediction efficacy.en_US
dc.description.sponsorshipNational Research Foundation of Koreaen_US
dc.description.sponsorshipNo Statement Availableen_US
dc.identifier.doi10.3390/math12050758
dc.identifier.issn2227-7390
dc.identifier.issue5en_US
dc.identifier.scopus2-s2.0-85187898408en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org10.3390/math12050758
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5006
dc.identifier.volume12en_US
dc.identifier.wosWOS:001181023500001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherMdpien_US
dc.relation.ispartofMathematicsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.snmz20240519_kaen_US
dc.subjectDeep Learning (Dl)en_US
dc.subjectSelf-Supervised Learning (Ssl)en_US
dc.subjectMachine Learning (Ml)en_US
dc.subjectCognitionen_US
dc.subjectClassificationen_US
dc.subjectData Annotationen_US
dc.titleConsequential Advancements of Self-Supervised Learning (SSL) in Deep Learning Contextsen_US
dc.typeReview Articleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu