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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

One of the current issues in Brain-Computer Interface is how to deal withnoisy Electroencephalography measurements organized as multidimensionaldatasets. On the other hand, recently, significant advances have been made inmultidimensional signal completion algorithms that exploit tensor decompositionmodels to capture the intricate relationship among entries in amultidimensional signal. We propose to use tensor completion applied to EEGdata for improving the classification performance in a motor imagery BCI systemwith corrupted measurements. Noisy measurements are considered as unknowns thatare inferred from a tensor decomposition model. We evaluate the performance offour recently proposed tensor completion algorithms plus a simple interpolationstrategy, first with random missing entries and then with missing samplesconstrained to have a specific structure (random missing channels), which is amore realistic assumption in BCI Applications. We measured the ability of thesealgorithms to reconstruct the tensor from observed data. Then, we tested theclassification accuracy of imagined movement in a BCI experiment with missingsamples. We show that for random missing entries, all tensor completionalgorithms can recover missing samples increasing the classificationperformance compared to a simple interpolation approach. For the random missingchannels case, we show that tensor completion algorithms help to reconstructmissing channels, significantly improving the accuracy in the classification ofmotor imagery, however, not at the same level as clean data. Tensor completionalgorithms are useful in real BCI applications. The proposed strategy couldallow using motor imagery BCI systems even when EEG data is highly affected bymissing channels and/or samples, avoiding the need of new acquisitions in thecalibration stage.

Brain-Computer Interface with Corrupted EEG Data: A Tensor Completion Approach