.png){kind=icon}
.png){kind=icon}
Return
Comparison of dimensionality reduction and feature selection for cognitive task decoding using functional connectivity
.png){kind=icon}
OA
AI
DOI：10.1016/j.jneumeth.2026.110746.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A suite of dimensionality reduction (DR) and feature selection (FS) methods were compared while using functional connectivity data. • Neither DR or FS was found to be superior. • A “sweet spot” of using 005%-10% of the total features was found to be optimal for decoding accuracy. • Ridge regression with a suite of DR/FS methods exceeded the performance of deep learning.
Keywords:
Dimensionality Reduction
Feature selection
Functional magnetic resonance imaging
Decoding
Machine Learning
Cognitive neuroscience
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.3
Papers:
426
Citations:
1.7W