Random Subspace Ensembles for fMRI Classification
- 2 February 2010
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 29 (2), 531-542
- https://doi.org/10.1109/tmi.2009.2037756
Abstract
Classification of brain images obtained through functional magnetic resonance imaging (fMRI) poses a serious challenge to pattern recognition and machine learning due to the extremely large feature-to-instance ratio. This calls for revision and adaptation of the current state-of-the-art classification methods. We investigate the suitability of the random subspace (RS) ensemble method for fMRI classification. RS samples from the original feature set and builds one (base) classifier on each subset. The ensemble assigns a class label by either majority voting or averaging of output probabilities. Looking for guidelines for setting the two parameters of the method-ensemble size and feature sample size-we introduce three criteria calculated through these parameters: usability of the selected feature sets, coverage of the set of ¿important¿ features, and feature set diversity. Optimized together, these criteria work toward producing accurate and diverse individual classifiers. RS was tested on three fMRI datasets from single-subject experiments: the Haxby data (Haxby, 2001.) and two datasets collected in-house. We found that RS with support vector machines (SVM) as the base classifier outperformed single classifiers as well as some of the most widely used classifier ensembles such as bagging, AdaBoost, random forest, and rotation forest. The closest rivals were the single SVM and bagging of SVM classifiers. We use kappa-error diagrams to understand the success of RS.This publication has 42 references indexed in Scilit:
- Neurofeedback: A promising tool for the self-regulation of emotion networksNeuroImage, 2010
- Local pattern classification differentiates processes of economic valuationNeuroImage, 2009
- Machine learning classifiers and fMRI: A tutorial overviewNeuroImage, 2009
- Sparse estimation automatically selects voxels relevant for the decoding of fMRI activity patternsNeuroImage, 2008
- Support vector machine learning-based fMRI data group analysisNeuroImage, 2007
- The impact of temporal compression and space selection on SVM analysis of single-subject and multi-subject fMRI dataNeuroImage, 2006
- Beyond mind-reading: multi-voxel pattern analysis of fMRI dataTrends in Cognitive Sciences, 2006
- Diversity creation methods: a survey and categorisationInformation Fusion, 2005
- Distributed and Overlapping Representations of Faces and Objects in Ventral Temporal CortexScience, 2001
- The random subspace method for constructing decision forestsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998