Advancing Medical Recommendations With Federated Learning on Decentralized Data: A Roadmap for Implementation

Basit Öğe Kaydı
dc.contributor.authorKumari, R.
dc.contributor.authorSah, D.K.
dc.contributor.authorGupta, S.
dc.contributor.authorCengiz, K.
dc.contributor.authorIvkovic, N.
dc.date.accessioned2024-05-19T14:33:48Z
dc.date.available2024-05-19T14:33:48Z
dc.date.issued2023
dc.departmentİstinye Üniversitesien_US
dc.description.abstractThis proposal presents a road-map for implementing federated learning for personalized medical recommendations on decentralized data. Federated learning is a privacy-preserving technique allowing multiple parties to train machine learning models collaboratively without sharing their data. Our proposed framework incorporates differential privacy techniques to protect patient privacy. We discuss several evaluation metrics, including KL divergence, fairness, confidence intervals, top-N hit rate, sensitivity analysis, and novelty to evaluate the performance of the federated learning system.These metrics collectively serve as a robust toolbox for assessing the performance of the federated learning system. The proposed framework and evaluation metrics can provide valuable insights into the system’s effectiveness and guide the selection of optimal hyperparameters and model architectures. Our framework incorporates differential privacy methods to safeguard patient information effectively. IEEEen_US
dc.identifier.doi10.1109/TCE.2023.3334159
dc.identifier.endpage1en_US
dc.identifier.issn0098-3063
dc.identifier.scopus2-s2.0-85179096453en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage1en_US
dc.identifier.urihttps://doi.org/10.1109/TCE.2023.3334159
dc.identifier.urihttps://hdl.handle.net/20.500.12713/4337
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofIEEE Transactions on Consumer Electronicsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectData Modelsen_US
dc.subjectData Privacyen_US
dc.subjectDecentralized Dataen_US
dc.subjectDistributed Databasesen_US
dc.subjectFederated Learningen_US
dc.subjectFederated Learningen_US
dc.subjectMedical Diagnostic İmagingen_US
dc.subjectMedical Servicesen_US
dc.subjectModel Architectureen_US
dc.subjectPersonalized Medical Recommendationsen_US
dc.subjectSensitivity Analysisen_US
dc.subjectTrainingen_US
dc.titleAdvancing Medical Recommendations With Federated Learning on Decentralized Data: A Roadmap for Implementationen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Bilgisayar Mühendisliği Bölümü Makale Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu