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

Federated edge learning (FEEL) enables privacy-preserving model trainingthrough periodic communication between edge devices and the server. UnmannedAerial Vehicle (UAV)-mounted edge devices are particularly advantageous forFEEL due to their flexibility and mobility in efficient data collection. InUAV-assisted FEEL, sensing, computation, and communication are coupled andcompete for limited onboard resources, and UAV deployment also affects sensingand communication performance. Therefore, the joint design of UAV deploymentand resource allocation is crucial to achieving the optimal trainingperformance. In this paper, we address the problem of joint UAV deploymentdesign and resource allocation for FEEL via a concrete case study of humanmotion recognition based on wireless sensing. We first analyze the impact ofUAV deployment on the sensing quality and identify a threshold value for thesensing elevation angle that guarantees a satisfactory quality of data samples.Due to the non-ideal sensing channels, we consider the probabilistic sensingmodel, where the successful sensing probability of each UAV is determined byits position. Then, we derive the upper bound of the FEEL training loss as afunction of the sensing probability. Theoretical results suggest that theconvergence rate can be improved if UAVs have a uniform successful sensingprobability. Based on this analysis, we formulate a training time minimizationproblem by jointly optimizing UAV deployment, integrated sensing, computation,and communication (ISCC) resources under a desirable optimality gap constraint.To solve this challenging mixed-integer non-convex problem, we apply thealternating optimization technique, and propose the bandwidth, batch size, andposition optimization (BBPO) scheme to optimize these three decision variablesalternately.

Integrated Sensing, Computation, and Communication for UAV-assisted Federated Edge Learning