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

In this paper, we consider voxel selection for functional Magnetic ResonanceImaging (fMRI) brain data with the aim of finding a more complete set ofprobably correlated discriminative voxels, thus improving interpretation of thediscovered potential biomarkers. The main difficulty in doing this is anextremely high dimensional voxel space and few training samples, resulting inunreliable feature selection. In order to deal with the difficulty, stabilityselection has received a great deal of attention lately, especially due to itsfinite sample control of false discoveries and transparent principle forchoosing a proper amount of regularization. However, it fails to make explicituse of the correlation property or structural information of thesediscriminative features and leads to large false negative rates. In otherwords, many relevant but probably correlated discriminative voxels are missed.Thus, we propose a new variant on stability selection "randomized structuralsparsity", which incorporates the idea of structural sparsity. Numericalexperiments demonstrate that our method can be superior in controlling forfalse negatives while also keeping the control of false positives inheritedfrom stability selection.

Randomized Structural Sparsity via Constrained Block Subsampling for Improved Sensitivity of Discriminative Voxel Identification