Naive random subspace ensemble with linear classifiers for real-time classification of fMRI data

Authors:
Catrin O. Plumpton;Ludmila I. Kuncheva;Nikolaas N. Oosterhof;Stephen J. Johnston
Affiliations:
School of Computer Science, Bangor University, Bangor, Gwynedd LL57 1UT, United Kingdom;School of Computer Science, Bangor University, Bangor, Gwynedd LL57 1UT, United Kingdom;School of Psychology, Bangor University, Bangor, Gwynedd LL57 2AS, United Kingdom;Psychology Department, Brunel University, Uxbridge, Middlesex UB8 3PH, United Kingdom
Venue:
Pattern Recognition
Year:
2012

Citing 9
Cited 5

The Random Subspace Method for Constructing Decision Forests

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
Using unlabeled data to improve text classification

Using unlabeled data to improve text classification
Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
Classifier geometrical characteristic comparison and its application in classifier selection

Pattern Recognition Letters
A case-study on naïve labelling for the nearest mean and the linear discriminant classifiers

Pattern Recognition
Adaptive Learning Rate for Online Linear Discriminant Classifiers

SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Using Real-Time fMRI to Control a Dynamical System by Brain Activity Classification

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I
On-Line fMRI Data Classification Using Linear and Ensemble Classifiers

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition

Editorial: Brain decoding: Opportunities and challenges for pattern recognition

Pattern Recognition
Online semi-supervised ensemble updates for fMRI data

PSL'11 Proceedings of the First IAPR TC3 conference on Partially Supervised Learning
A survey of multiple classifier systems as hybrid systems

Information Fusion
Learning ensemble classifiers via restricted Boltzmann machines

Pattern Recognition Letters
A case study of linear classifiers adapted using imperfect labels derived from human event-related potentials

Pattern Recognition Letters

Quantified Score

Hi-index	0.01

Visualization

Abstract

Functional magnetic resonance imaging (fMRI) provides a spatially accurate measure of brain activity. Real-time classification allows the use of fMRI in neurofeedback experiments. With limited labelled data available, a fixed pre-trained classifier may be inaccurate. We propose that streaming fMRI data may be classified using a classifier ensemble which is updated through naive labelling. Naive labelling is a protocol where in the absence of ground truth, updates are carried out using the label assigned by the classifier. We perform experiments on three fMRI datasets to demonstrate that naive labelling is able to improve upon a pre-trained initial classifier.