Evaluation of Markov Blanket Algorithms for fMRI Data Analysis
Aiming at the extraction and selection of features for localization of the areas of the brain that have been activated by a predefined stimulus, this paper presents an approach to select features of fMRI datasets using Bayesian Network and Markov Blanket. When a large data set is of interest selecting relevant features is in demand in a classification task. It produces a tractable number of features that are sufficient and possibly improve the classification performance. The activity patterns in functional Magnetic Resonance Imaging (fMRI) data are unique and located in specific location in the brain.