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

Assisted and autonomous driving are rapidly gaining momentum, and will soonbecome a reality. Among their key enablers, artificial intelligence and machinelearning are expected to play a prominent role, also thanks to the massiveamount of data that smart vehicles will collect from their onboard sensors. Inthis domain, federated learning is one of the most effective and promisingtechniques for training global machine learning models, while preserving dataprivacy at the vehicles and optimizing communications resource usage. In thiswork, we propose VREM-FL, a computation-scheduling co-design for vehicularfederated learning that leverages mobility of vehicles in conjunction withestimated 5G radio environment maps. VREM-FL jointly optimizes the global modellearned at the server while wisely allocating communication resources. This isachieved by orchestrating local computations at the vehicles in conjunctionwith the transmission of their local model updates in an adaptive andpredictive fashion, by exploiting radio channel maps. The proposed algorithmcan be tuned to trade model training time for radio resource usage.Experimental results demonstrate the efficacy of utilizing radio maps. VREM-FLoutperforms literature benchmarks for both a linear regression model (learningtime reduced by 28%) and a deep neural network for a semantic imagesegmentation task (doubling the number of model updates within the same timewindow).

VREM-FL: Mobility-Aware Computation-Scheduling Co-Design for Vehicular Federated Learning