Durrant, Simon and Hardoon, D. R. and Brechmann, A. and Shawe-Taylor, J. and Miranda, E. R. and Scheich, H. (2009) GLM and SVM analyses of neural response to tonal and atonal stimuli: new techniques and a comparison. Connection Science, 21 (2-3). pp. 161-175. ISSN 0954-0091

PDF GLM_and_SVM_analyses_of_neural_response_to_tonal_and_atonal_stimuli_-_new_techniques_and_a_comparison_(Durrant_2009).pdf - Whole Document Restricted to Repository staff only Download (1406Kb) | Request a copy

Abstract

This paper gives both general linear model (GLM) and support vector machine (SVM) analyses of an experiment concerned with tonality in music. The two forms of analysis are both contrasted and used to complement each other, and a new technique employing the GLM as a pre-processing step for the SVM is presented. The SVM is given the task of classifying the stimulus conditions (tonal or atonal) on the basis of the blood oxygen level-dependent signal of novel data, and the prediction performance is evaluated. In addition, a more detailed assessment of the SVM performance is given in a comparison of the similarity in the identification of voxels relevant to the classification of the SVM and a GLM.A high level of similarity between SVM weight and GLM t-maps demonstrate that the SVM is successfully identifying relevant voxels, and it is this that allows it to perform well in the classification task in spite of very noisy data and stimuli that involve higher-order cognitive functions and considerably inter-subject variation in neural response.

Item Type:	Article
Additional Information:	This paper gives both general linear model (GLM) and support vector machine (SVM) analyses of an experiment concerned with tonality in music. The two forms of analysis are both contrasted and used to complement each other, and a new technique employing the GLM as a pre-processing step for the SVM is presented. The SVM is given the task of classifying the stimulus conditions (tonal or atonal) on the basis of the blood oxygen level-dependent signal of novel data, and the prediction performance is evaluated. In addition, a more detailed assessment of the SVM performance is given in a comparison of the similarity in the identification of voxels relevant to the classification of the SVM and a GLM.A high level of similarity between SVM weight and GLM t-maps demonstrate that the SVM is successfully identifying relevant voxels, and it is this that allows it to perform well in the classification task in spite of very noisy data and stimuli that involve higher-order cognitive functions and considerably inter-subject variation in neural response.
Keywords:	fMRI, support vector machine, general linear model, music cognition, machine learning
Subjects:	C Biological Sciences > C800 Psychology C Biological Sciences > C850 Cognitive Psychology C Biological Sciences > C860 Neuropsychology
Divisions:	College of Social Sciences > Faculty of Health & Social Sciences > School of Psychology
Depositing User:	Alison Wilson
Date Deposited:	12 Oct 2011 06:48
Last Modified:	13 Mar 2013 09:02
URI:	http://eprints.lincoln.ac.uk/id/eprint/4722

Actions (login required)

View Item