fMRI classification based on analysis of variance combined with support vector machine

To relieve the curse of dimensionality in functional magnetic resonance imaging (fMRI), we combine analysis of variance (ANOVA) with a support vector machine (SVM) to form a feature-based classification method. ANOVA is applied to find a more compact representation of the data by extracting features from fMRI images. A linear kernel SVM classifier is then trained on the selected features. Combining ANOVA with SVM significantly reduces the computational burden of the SVM process and establishes a less complex classifier. Experiments using Haxby´s dataset to classify fMRI images show that the proposed method yields good performance, with an average accuracy of up to 96.25%.