As the field of functional human brain mapping has matured, it has become apparent that a comprehensive understanding of the human brain, and its relationship with cognition, will require a quantitative assessment of individual differences in both brain function and structure. To assess brain structure, accurate classification of magnetic resonance images needed. In recent years, functional Magnetic Resonance Imaging (fMRI) has emerged as a powerful new instrument to collect vast quantities of data about activity in the human brain. As in other modern empirical sciences, this new instrumentation has led to a flood of new data and a corresponding need for new data analysis methods. A standard fMRI study gives rise to massive amounts of noisy data with a complicated spatio-temporal correlation structure. In this paper we discuss the analysis of fMRI data, from the angle of support vector machine classification for analysis of complex, multivariate data.
Swain, Ramakrushna; Jena, Lambodar; and Kamila, Narendra K.
"Cognitive States from Brain Images : SVM Approach,"
International Journal of Computer and Communication Technology: Vol. 3
, Article 12.
Available at: https://www.interscience.in/ijcct/vol3/iss2/12