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

Brain-computer interface (BCI) aims to establish and improve human andcomputer interactions. There has been an increasing interest in designing newhardware devices to facilitate the collection of brain signals through varioustechnologies, such as wet and dry electroencephalogram (EEG) and functionalnear-infrared spectroscopy (fNIRS) devices. The promising results of machinelearning methods have attracted researchers to apply these methods to theirdata. However, some methods can be overlooked simply due to their inferiorperformance against a particular dataset. This paper shows how relativelysimple yet powerful feature selection/ranking methods can be applied to speechimagery datasets and generate significant results. To do so, we introduce twoapproaches, horizontal and vertical settings, to use any feature selection andranking methods to speech imagery BCI datasets. Our primary goal is to improvethe resulting classification accuracies from support vector machines,$k$-nearest neighbour, decision tree, linear discriminant analysis and longshort-term memory recurrent neural network classifiers. Our experimentalresults show that using a small subset of channels, we can retain and, in mostcases, improve the resulting classification accuracies regardless of theclassifier.

Revisiting the Application of Feature Selection Methods to Speech Imagery BCI Datasets