Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Fast, Accurate, and Stable Feature Selection Using Neural Networks

Fast, Accurate, and Stable Feature Selection Using Neural Networks Multi-voxel pattern analysis often necessitates feature selection due to the high dimensional nature of neuroimaging data. In this context, feature selection techniques serve the dual purpose of potentially increasing classification accuracy and revealing sets of features that best discriminate between classes. However, feature selection techniques in current, widespread use in the literature suffer from a number of deficits, including the need for extended computational time, lack of consistency in selecting features relevant to classification, and only marginal increases in classifier accuracy. In this paper we present a novel method for feature selection based on a single-layer neural network which incorporates cross-validation during feature selection and stability selection through iterative subsampling. Comparing our approach to popular alternative feature selection methods, we find increased classifier accuracy, reduced computational cost and greater consistency with which relevant features are selected. Furthermore, we demonstrate that importance mapping, a technique used to identify voxels relevant to classification, can lead to the selection of irrelevant voxels due to shared activation patterns across categories. Our method, owing to its relatively simple architecture, flexibility and speed, can provide a viable alternative for researchers to identify sets of features that best discriminate classes. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neuroinformatics Springer Journals

Fast, Accurate, and Stable Feature Selection Using Neural Networks

Neuroinformatics , Volume 16 (2) – Mar 21, 2018

Loading next page...
 
/lp/springer-journals/fast-accurate-and-stable-feature-selection-using-neural-networks-8a4tnjJVus

References (72)

Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer Science+Business Media, LLC, part of Springer Nature
Subject
Biomedicine; Neurosciences; Bioinformatics; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Neurology
ISSN
1539-2791
eISSN
1559-0089
DOI
10.1007/s12021-018-9371-3
Publisher site
See Article on Publisher Site

Abstract

Multi-voxel pattern analysis often necessitates feature selection due to the high dimensional nature of neuroimaging data. In this context, feature selection techniques serve the dual purpose of potentially increasing classification accuracy and revealing sets of features that best discriminate between classes. However, feature selection techniques in current, widespread use in the literature suffer from a number of deficits, including the need for extended computational time, lack of consistency in selecting features relevant to classification, and only marginal increases in classifier accuracy. In this paper we present a novel method for feature selection based on a single-layer neural network which incorporates cross-validation during feature selection and stability selection through iterative subsampling. Comparing our approach to popular alternative feature selection methods, we find increased classifier accuracy, reduced computational cost and greater consistency with which relevant features are selected. Furthermore, we demonstrate that importance mapping, a technique used to identify voxels relevant to classification, can lead to the selection of irrelevant voxels due to shared activation patterns across categories. Our method, owing to its relatively simple architecture, flexibility and speed, can provide a viable alternative for researchers to identify sets of features that best discriminate classes.

Journal

NeuroinformaticsSpringer Journals

Published: Mar 21, 2018

There are no references for this article.