Абстрактный

Survey on Feature Subset Selection Algorithm in Brain Interaction Patterns

K.Vidhyadevia, M.Beema Mehraj, K.P.Kaliyamurthie

Functional magnetic resonance imaging (FMRI) patterns provides the prospective to study brain function in a non-invasive way. The FMRI data are time series of 3-dimensional volume images of the brain. The data is traditionally analyzed within a mass-univariate framework essentially relying on classical inferential statistics. Handling of feature selection and clustering is a complicated process in interaction patterns of brain datasets. To understand the complex interaction patterns among brain regions system proposes a novel clustering technique. System models each subject as multivariate time series, where the single dimensions characterize the FMRI signal at different anatomical regions. In this survey paper, compares various research parameters for detection of clusters of objects with similar interaction patterns classification and clustering techniques used in it. The study papers was effective to understand the techniques and gives idea to propose select the key features in the preprocessed dataset based on the threshold values and Dimension Ranking algorithm was used to select the best cluster for assuring best result.