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

We experimentally investigate a collection of feature engineering pipelinesfor use with a CNN for classifying eyes-open or eyes-closed fromelectroencephalogram (EEG) time-series from the Bonn dataset. Using the Takens'embedding--a geometric representation of time-series--we construct simplicialcomplexes from EEG data. We then compare $\epsilon$-series of Betti-numbers and$\epsilon$-series of graph spectra (a novel construction)--two topologicalinvariants of the latent geometry from these complexes--to raw time series ofthe EEG to fill in a gap in the literature for benchmarking. These methods,inspired by Topological Data Analysis, are used for feature engineering tocapture local geometry of the time-series. Additionally, we test these featurepipelines' robustness to downsampling and data reduction. This paper seeks toestablish clearer expectations for both time-series classification viageometric features, and how CNNs for time-series respond to data of degradedresolution.

Geometric feature performance under downsampling for EEG classification tasks