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

Widely available healthcare services are now getting popular because ofadvancements in wearable sensing techniques and mobile edge computing. People'shealth information is collected by edge devices such as smartphones andwearable bands for further analysis on servers, then send back suggestions andalerts for abnormal conditions. The recent emergence of federated learningallows users to train private data on local devices while updating modelscollaboratively. However, the heterogeneous distribution of the healthcondition data may lead to significant risks to model performance due to classimbalance. Meanwhile, as FL training is powered by sharing gradients only withthe server, training data is almost inaccessible. The conventional solutions toclass imbalance do not work for federated learning. In this work, we propose anew federated learning framework FedImT, dedicated to addressing the challengesof class imbalance in federated learning scenarios. FedImT contains an onlinescheme that can estimate the data composition during each round of aggregation,then introduces a self-attenuating iterative equivalent to track variations ofmultiple estimations and promptly tweak the balance of the loss computing forminority classes. Experiments demonstrate the effectiveness of FedImT insolving the imbalance problem without extra energy consumption and avoidingprivacy risks.

An Efficient Imbalance-Aware Federated Learning Approach for Wearable Healthcare with Autoregressive Ratio Observation