Abstract
The functional magnetic resonance imaging (fMRI) technique is a powerful imaging tool for analyzing the brain activity by localizing patterns of activity related to specific mental processes. Recently, researchers have started to solve the inverse problem of detecting the cognitive states at a particular point of time by applying the multi-voxel pattern classification approach. Since fMRI data are high dimensional, extremely sparse and noisy, feature selection is a key challenge in this kind of approach. In this paper, we propose a new method for selecting the most informative features from fMRI data. By computing Fisher Discriminant Ratio, we can identify the most active voxels from several Regions of Interest. These active voxels are considered as the most powerful discriminative features. We investigated the performance of this method by classifying the human’s cognitive states of “observing a picture” versus “reading a sentence”. The experimental results showed that our method achieved the highest accuracy compared to other feature selection methods with the Gaussian Naïve Bayes (GNB) classifier. The average accuracy of six human subjects is approximately 96.45%.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Lindquist, M.A.: The Statistical Analysis of fMRI Data. Statistical Science 28, 439–464 (2008)
Cox, D.D., Savoy, R.L.: Functional magnetic resonance imaging (fMRI) “brain reading”: Detecting and classifying distributed patterns of fMRI activity in human visual cortex. NeuroImage 19, 261–270 (2003)
Hoang, M.T.T., Won, Y.G., Yang, H.J.: Cognitive States Detection in fMRI Data Analysis using incremental PCA. In: ICCSA, pp. 335–341 (2007)
Yong, F., Shen, D., Davatzikos, C.: Detecting Cognitive States from fMRI Images by Machine Learning and Multivariate Classification. In: Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop (2006)
Etzel, J.A., Gazzola, V., Keysers, C.: An introduction to anatomical ROI-based fMRI classification analysis. Brain Research 1282, 114–125 (2009)
Bapi, R.S., Singh, V., Miyapuram, K.P.: Detection of Cognitive States from fMRI data using Machine Learning Techniques. In: IJCAI, pp. 587–592 (2007)
Ng, B., Vahdat, A., Hamarneh, G., Abugharbieh, R.: Generalized Sparse Classifiers for Decoding Cognitive States in fMRI. In: Wang, F., Yan, P., Suzuki, K., Shen, D. (eds.) MLMI 2010. LNCS, vol. 6357, pp. 108–115. Springer, Heidelberg (2010)
Mitchell, T.M., Hutchinson, R., Niculescu, R.S., Pereira, F., Wang, X., Just, M., Newman, S.: Learning to decode Cognitive States from Brain Images. Machine Learning 57, 145–175 (2004)
Rademacher, J., Galaburda, A.M., Kennedy, D.N., Filipek, P.A., Caviness, V.S.: Human celebral cortex: Localization, parcellation, and morphometry with magnetic resonance imaging. Journal of Cognitive Neuroscience 4, 352–374 (1992)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Do, LN., Yang, HJ. (2014). A Robust Feature Selection Method for Classification of Cognitive States with fMRI Data. In: Jeong, H., S. Obaidat, M., Yen, N., Park, J. (eds) Advances in Computer Science and its Applications. Lecture Notes in Electrical Engineering, vol 279. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41674-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-41674-3_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41673-6
Online ISBN: 978-3-642-41674-3
eBook Packages: EngineeringEngineering (R0)