Multiple particle swarm optimization selection techniques for fMRI classification of schizophrenia patients

Abstract

Magnetic Resonance Imaging MRI is a medical imaging technique mainly used by the radiologist for the visual examination of the internal structure of the human body without any surgery MRI provides plentiful information about the human soft tissue which helps in the diagnosis of brain tumour Functional MRI fMRI currently the most advanced technology is at the disposal of cognitive neuroscience It measures Blood Oxygenation Level Dependent BOLD signal and tries to discover how mental states are mapped onto patterns of neural activity Feature selection has been recast as voxel selection ie determining voxels in the brain relevant for discrimination between mental states While feature selection and classification are intrinsically related they are often performed separately Feature selection and classification of fMRI data have been described as a newlineformidable analytic challenge Feature selection techniques are explored for dimensionality reduction which are intuitive and map back easily into large original feature space for interpretation In this work the Support Vector Machine SVM Independent Component Analysis ICA and Particle Swarm Optimization PSO based feature selections are proposed ICA refers to separating the liberated sources from its obtained linear mixture In ICA technique the observations are the only information possessed and there is no knowledge of the mixing matrix or the distribution of sources PSO serves to be a stochastic method based on the swarming behavior of birds and fish newline newline