English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Internet of Medical Things (IoMT) is becoming ubiquitous with a proliferationof smart medical devices and applications used in smart hospitals, smart-homebased care, and nursing homes. It utilizes smart medical devices and cloudcomputing services along with core Internet of Things (IoT) technologies tosense patients' vital body parameters, monitor health conditions and generatemultivariate data to support just-in-time health services. Mostly, this largeamount of data is analyzed in centralized servers. Anomaly Detection (AD) in acentralized healthcare ecosystem is often plagued by significant delays inresponse time with high performance overhead. Moreover, there are inherentprivacy issues associated with sending patients' personal health data to acentralized server, which may also introduce several security threats to the ADmodel, such as possibility of data poisoning. To overcome these issues withcentralized AD models, here we propose a Federated Learning (FL) based AD modelwhich utilizes edge cloudlets to run AD models locally without sharingpatients' data. Since existing FL approaches perform aggregation on a singleserver which restricts the scope of FL, in this paper, we introduce ahierarchical FL that allows aggregation at different levels enablingmulti-party collaboration. We introduce a novel disease-based groupingmechanism where different AD models are grouped based on specific types ofdiseases. Furthermore, we develop a new Federated Time Distributed (FedTimeDis)Long Short-Term Memory (LSTM) approach to train the AD model. We present aRemote Patient Monitoring (RPM) use case to demonstrate our model, andillustrate a proof-of-concept implementation using Digital Twin (DT) and edgecloudlets.

Hierarchical Federated Learning based Anomaly Detection using Digital Twins for Smart Healthcare