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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Objective. The main goal of this work is to develop a model for multi-sensorsignals such as MEG or EEG signals, that accounts for the inter-trialvariability, suitable for corresponding binary classification problems. Animportant constraint is that the model be simple enough to handle small sizeand unbalanced datasets, as often encountered in BCI type experiments.Approach. The method involves linear mixed effects statistical model, wavelettransform and spatial filtering, and aims at the characterization of localizeddiscriminant features in multi-sensor signals. After discrete wavelet transformand spatial filtering, a projection onto the relevant wavelet and spatialchannels subspaces is used for dimension reduction. The projected signals arethen decomposed as the sum of a signal of interest (i.e. discriminant) andbackground noise, using a very simple Gaussian linear mixed model. Mainresults. Thanks to the simplicity of the model, the corresponding parameterestimation problem is simplified. Robust estimates of class-covariance matricesare obtained from small sample sizes and an effective Bayes plug-in classifieris derived. The approach is applied to the detection of error potentials inmultichannel EEG data, in a very unbalanced situation (detection of rareevents). Classification results prove the relevance of the proposed approach insuch a context. Significance. The combination of linear mixed model, wavelettransform and spatial filtering for EEG classification is, to the best of ourknowledge, an original approach, which is proven to be effective. This paperimproves on earlier results on similar problems, and the three main ingredientsall play an important role.

Detecting single-trial EEG evoked potential using a wavelet domain linear mixed model: application to error potentials classification