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

With the enhancement of people's living standards and rapid growth ofcommunication technologies, residential environments are becoming smart andwell-connected, increasing overall energy consumption substantially. Ashousehold appliances are the primary energy consumers, their recognitionbecomes crucial to avoid unattended usage, thereby conserving energy and makingsmart environments more sustainable. An appliance recognition model istraditionally trained at a central server (service provider) by collectingelectricity consumption data, recorded via smart plugs, from the clients(consumers), causing a privacy breach. Besides that, the data are susceptibleto noisy labels that may appear when an appliance gets connected to anon-designated smart plug. While addressing these issues jointly, we propose anovel federated learning approach to appliance recognition, called FedAR+,enabling decentralized model training across clients in a privacy preservingway even with mislabeled training data. FedAR+ introduces an adaptive noisehandling method, essentially a joint loss function incorporating weights andlabel distribution, to empower the appliance recognition model against noisylabels. By deploying smart plugs in an apartment complex, we collect a labeleddataset that, along with two existing datasets, are utilized to evaluate theperformance of FedAR+. Experimental results show that our approach caneffectively handle up to $30\%$ concentration of noisy labels whileoutperforming the prior solutions by a large margin on accuracy.

FedAR+: A Federated Learning Approach to Appliance Recognition with Mislabeled Data in Residential Buildings