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

Many cognitive, sensory and motor processes have correlates in oscillatoryneural sources, which are embedded as a subspace into the recorded brainsignals. Decoding such processes from noisymagnetoencephalogram/electroencephalogram (M/EEG) signals usually requires theuse of data-driven analysis methods. The objective evaluation of such decodingalgorithms on experimental raw signals, however, is a challenge: the amount ofavailable M/EEG data typically is limited, labels can be unreliable, and rawsignals often are contaminated with artifacts. The latter is specificallyproblematic, if the artifacts stem from behavioral confounds of the oscillatoryneural processes of interest.  To overcome some of these problems, simulation frameworks have beenintroduced for benchmarking decoding methods. Generating artificial brainsignals, however, most simulation frameworks make strong and partiallyunrealistic assumptions about brain activity, which limits the generalizationof obtained results to real-world conditions.  In the present contribution, we thrive to remove many shortcomings of currentsimulation frameworks and propose a versatile alternative, that allows forobjective evaluation and benchmarking of novel data-driven decoding methods forneural signals. Its central idea is to utilize post-hoc labelings of arbitraryM/EEG recordings. This strategy makes it paradigm-agnostic and allows togenerate comparatively large datasets with noiseless labels. Source code anddata of the novel simulation approach are made available for facilitating itsadoption.

Post-hoc labeling of arbitrary EEG recordings for data-efficient evaluation of neural decoding methods