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

The decoding of brain signals recorded via, e.g., an electroencephalogram,using machine learning is key to brain-computer interfaces (BCIs). Stimulationparameters or other experimental settings of the BCI protocol typically arechosen according to the literature. The decoding performance directly dependson the choice of parameters, as they influence the elicited brain signals andoptimal parameters are subject-dependent. Thus a fast and automated selectionprocedure for experimental parameters could greatly improve the usability ofBCIs.  We evaluate a standalone random search and a combined Bayesian optimizationwith random search in a closed-loop auditory event-related potential protocol.We aimed at finding the individually best stimulation speed -- also known asstimulus onset asynchrony (SOA) -- that maximizes the classificationperformance of a regularized linear discriminant analysis. To make the Bayesianoptimization feasible under noise and the time pressure posed by an online BCIexperiment, we first used offline simulations to initialize and constrain theinternal optimization model. Then we evaluated our approach online with 13healthy subjects.  We could show that for 8 out of 13 subjects, the proposed approach usingBayesian optimization succeeded to select the individually optimal SOA out ofmultiple evaluated SOA values. Our data suggests, however, that subjects wereinfluenced to very different degrees by the SOA parameter. This makes theautomatic parameter selection infeasible for subjects where the influence islimited.  Our work proposes an approach to exploit the benefits of individualizedexperimental protocols and evaluated it in an auditory BCI. When applied toother experimental parameters our approach could enhance the usability of BCIfor different target groups -- specifically if an individual disease progressmay prevent the use of standard parameters.

Online Optimization of Stimulation Speed in an Auditory Brain-Computer Interface under Time Constraints