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

Electroencephalografic (EEG) data are complex multi-dimensional time-seriesthat are very useful in many applications, from diagnostics to drivingbrain-computer interface systems. Their classification is still a challengingtask, due to the inherent within- and between-subject variability and their lowsignal-to-noise ratio. On the other hand, the reconstruction of raw EEG data iseven more difficult because of the high temporal resolution of these signals.Recent literature has proposed numerous machine and deep learning models thatcould classify, e.g., different types of movements, with an accuracy in therange 70% to 80% (with 4 classes). On the other hand, a limited number of workstargeted the reconstruction problem, with very limited results. In this work,we propose vEEGNet, a DL architecture with two modules, i.e., an unsupervisedmodule based on variational autoencoders to extract a latent representation ofthe data, and a supervised module based on a feed-forward neural network toclassify different movements. To build the encoder and the decoder of VAE weexploited the well-known EEGNet network. We implemented two slightly differentarchitectures of vEEGNet, thus showing state-of-the-art classificationperformance, and the ability to reconstruct both low-frequency and middle-rangecomponents of the raw EEG. Although preliminary, this work is promising as wefound out that the low-frequency reconstructed signals are consistent with theso-called motor-related cortical potentials, well-known motor-related EEGpatterns and we could improve over previous literature by reconstructing fasterEEG components, too. Further investigations are needed to explore thepotentialities of vEEGNet in reconstructing the full EEG data, generating newsamples, and studying the relationship between classification andreconstruction performance.

vEEGNet: learning latent representations to reconstruct EEG raw data via variational autoencoders