A Genetic algorithm based feature selection technique for classification of multiple-subject fMRI data

Functional Magnetic Resonance Imaging (fMRI) is a neuroimaging technique used to capture images of brain activity. These images have high spatial resolution and hence are very high dimensional. Each scan consists of more than one hundred thousand voxels. All of the scanned voxels are not activated for every stimulus. Therefore, finding the informative voxels with respect to stimulus becomes a prerequisite for any machine learning solution using fMRI data. The specific problem attempted to be solved in this paper is that of decoding cognitive states from multiple-subject fMRI data. Decoding multiple-subject data is challenging owing to the difference in the shape and size of the brain of different subjects. A Genetic algorithm based technique is proposed here for selection of voxels that capture commonality across subjects. Some popular feature selection techniques are compared against Genetic algorithms. It is observed that feature selection using Genetic algorithms perform consistently and predictably better than other techniques.