An efficient FMRI classification technique in cloud using multiple parallel feature selection algorithm

Abstract

Extensive research is going on in the field of analyzing the applications involving functional magnetic resonance imaging (fMRI) data with the help of machine learning classifiers. Studies have proven that inspiring new information can be obtained through neuroimaging data using machine learning classifiers. Feature selection has been an active research area and its key idea is to select a subset of input variables by removing features with little or no predictive data. Feature selection enhanced the clarity of the resulting classifier models and often dimensions a model that generalizes better to unseen points. In this work, fMRI classification technique is proposed using Multiple Parallel Feature Selection Algorithm. In case of parallel feature selection, the proposed algorithm’s computation is fully improved and parallelized based on data partitioning. Inputs for classifiers are used extensively through voxel-based features. The fMRI images are classified as normal or abnormal. From healthy persons normal fMRI images were obtained and from subjects with schizophrenia abnormal fMRI were obtained and a total of 140 normal fMRI and 67 abnormal fMRI were used. Multiple particle swarm optimization was used after independent component analysis phase and techniques varying by c1 and c2 were used through cluster computing techniques. From the obtained cluster the feature subset was selected and support vector machine is made use in classifying.