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

Split Learning (SL) is a promising Distributed Learning approach inelectromyography (EMG) based prosthetic control, due to its applicabilitywithin resource-constrained environments. Other learning approaches, such asDeep Learning and Federated Learning (FL), provide suboptimal solutions, sinceprosthetic devices are extremely limited in terms of processing power andbattery life. The viability of implementing SL in such scenarios is caused byits inherent model partitioning, with clients executing the smaller modelsegment. However, selecting an inadequate cut layer hinders the trainingprocess in SL systems. This paper presents an algorithm for optimal cut layerselection in terms of maximizing the convergence rate of the model. Theperformance evaluation demonstrates that the proposed algorithm substantiallyaccelerates the convergence in an EMG pattern recognition task for improvingprosthetic device control.

Convergence Rate Maximization for Split Learning-based Control of EMG Prosthetic Devices