• Home
  • Search
  • Comparison of dimensionality reduction and feature selection for cognitive task decoding using functional connectivity.
  • https://doi.org/10.1016/j.jneumeth.2026.110746Copy DOI Icon

Comparison of dimensionality reduction and feature selection for cognitive task decoding using functional connectivity.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Advances in functional magnetic resonance imaging (fMRI) have led to the ability to study the brain across many contexts. However, the large number of features generated by functional connectivity approaches may overfit the data. These problems can be overcome with either feature selection (FS) or dimensionality reduction (DR), which can be applied to less complex models. We utilize two open source datasets to compare the performance of DR/FS methods on cognitive task decoding using a suite of ML classifiers. While FS and DR methods have been used previously in decoding research, no systematic comparison of their performance has been undertaken. Here, we compare available methods using commonly utilized machine learning libraries to establish which methods provide the best predictive performance. We then conduct statistical tests to examine the relative contributions of DR and FS methods and classifiers on decoding accuracy. Neither DR or FS was found to be superior. However, differences were identified across datasets and tasks. In the majority of methods and datasets, a peak in predictive performance was found using a small percentage (005-.10%) of the total number of original features. Some methods perform better than the baseline method of prediction with all available features or selecting features randomly. Decoding performance with some datasets with some method exceeds that of deep learning approaches. These results suggest a "sweet spot" for the tradeoff between the retention of features and predictive accuracy.

Similar Papers
  • Conference Article
  • Citations2

Advanced LLE Method for Dimension Reduction using Nonlinear Manufacturing Data

  • Sep 01, 2018
  • Sitong Xu +3
  • Research Article
  • Citations5

MCDM-EFS: A novel ensemble feature selection method for software defect prediction using multi-criteria decision making

  • Nov 20, 2023
  • Intelligent Decision Technologies
  • Kamaldeep Kaur +1
  • Conference Article
  • Citations1193

A survey of feature selection and feature extraction techniques in machine learning

  • Aug 01, 2014
  • Samina Khalid +2
  • Conference Article

Cancer data classification using a fuzzy classifier based on bio-inspired algorithms

  • Aug 01, 2015
  • Jamshid Pirgazi +2
  • PDF
  • Research Article
  • Citations18

Feature Selection and Feature Stability Measurement Method for High-Dimensional Small Sample Data Based on Big Data Technology.

  • Jan 01, 2021
  • Computational Intelligence and Neuroscience
  • Chengyuan Huang
  • Conference Article
  • Citations1

A Graph Theoretic Based Feature Selection Method Using Multi Objective PSO

  • Aug 04, 2020
  • S Azadifar +1
  • PDF
  • Research Article
  • Citations11

Hybrid Machine Learning Model for Electricity Consumption Prediction Using Random Forest and Artificial Neural Networks

  • Apr 21, 2022
  • Applied Computational Intelligence and Soft Computing
  • Witwisit Kesornsit +1
  • Conference Article

Investigation of different dimension reduction and normalization methods for local appearance-based face recognition

  • Apr 01, 2009
  • Berkay Topcu +1
  • PDF
  • Research Article
  • Citations22

Prediction of hot spots in protein\u2013DNA binding interfaces based on supervised isometric feature mapping and extreme gradient boosting

  • Sep 01, 2020
  • BMC Bioinformatics
  • Ke Li +4
  • Research Article
  • Citations43

QSAR analysis of diaryl COX-2 inhibitors: Comparison of feature selection and train-test data selection methods

  • Mar 01, 2010
  • European Journal of Medicinal Chemistry
  • Somaieh Soltani +3
  • Research Article
  • Citations29

A Harmony Search Based Wrapper Feature Selection Method for Holistic Bangla Word Recognition

  • Jan 01, 2016
  • Procedia Computer Science
  • Supratim Das +4
  • Research Article
  • Citations77

Benchmarking Feature Selection Methods in Radiomics.

  • Jan 18, 2022
  • Investigative Radiology
  • Aydin Demircioğlu
  • Conference Article
  • Citations3

Two-Step Feature Selection Methods for Selection of Very Few Features

  • Nov 01, 2016
  • Peter Drotar +1
  • Research Article
  • Citations50

Combining Handcrafted Features with Latent Variables in Machine Learning for Prediction of Radiation-Induced Lung Damage

  • Apr 08, 2019
  • Medical physics
  • Sunan Cui +4
  • Research Article
  • Citations58

Sparse non-negative generalized PCA with applications to metabolomics

  • Sep 19, 2011
  • Bioinformatics
  • Genevera I Allen +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.