Kernel methods for fmri pattern prediction

Y Ni, Chu C., Saunders C., Ashburner J.

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

4 Citations (Scopus)

Abstract

In this paper, we present an effective computational approach for learning patterns of brain activity from the fMRI data. The procedure involved correcting motion artifacts, spatial smoothing, removing low frequency drifts and applying multivariate linear and non-linear kernel methods. Two novel techniques are applied: one utilizes the Cosine Transform to remove low-frequency drifts over time and the other involves using prior knowledge about the spatial contribution of different brain regions for the various tasks. Our experiment results on the PBAIC2007 competition data set show a great improvement for brain activity prediction, especially on some sensory experience such as hearing and vision.
Translated title of the contributionKernel methods for fmri pattern prediction
Original languageEnglish
Title of host publicationthe International Joint Conference on Neural Networks, Hong Kong
Publication statusPublished - 2008

Bibliographical note

Conference Organiser: WCCI

Fingerprint Dive into the research topics of 'Kernel methods for fmri pattern prediction'. Together they form a unique fingerprint.

  • Cite this

    Ni, Y., C., C., C., S., & J., A. (2008). Kernel methods for fmri pattern prediction. In the International Joint Conference on Neural Networks, Hong Kong http://patterns.enm.bris.ac.uk/publications/kernel-methods-for-fmri-pattern-prediction#