Blockchain-Based Personalized Federated Learning for Internet of Medical Things

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

11 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Journal / PublicationIEEE Transactions on Sustainable Computing
Publication statusOnline published - 23 May 2023

Abstract

The rapid growth of artificial intelligence (AI), blockchain technology, and edge computing services have enabled the Internet of Medical Things (IoMT) to provide various healthcare services to patients, including neural network-based disease diagnosis, heart rate monitoring, and fall detection. Generally, end devices should transmit the collected patient data to a centralized server for further model training, but at the same time, the patient's privacy may be at risk. In addition, due to the diversity of patient conditions, a one-size-fits-all model cannot meet personalized healthcare needs. To address the above challenges, we propose a blockchain-based personalized federated learning (FL) system that enables clients to participate in personalized model training without directly uploading private data. We further realize the decentralized FL by combining blockchain technology, which improves the security level of the system. Finally, we verify the reliable performance of our system on different datasets through simulation experiments. © 2023 IEEE.

Research Area(s)

  • Blockchain, Blockchains, Data models, federated learning, internet of medical things, Medical services, Monitoring, privacy-preserving, Security, Training