In this paper an application of genetic algorithms (GAs) and Gaussian Naïve Bayesian (GNB) approach is studied to explore the brain activities by decoding specific cognitive states from functional magnetic resonance imaging (fMRI) data. However, in case of fMRI data analysis the large number of attributes may leads to a serious problem of classifying cognitive states. It significantly increases the computational cost and memory usage of a classifier. Hence to address this problem, we use GAs for selecting optimal set of attributes and then GNB classifier in a pipeline to classify different cognitive states. The experimental outcomes prove its worthiness in successfully classifying different cognitive states. The detailed comparison study with popular machine learning classifiers illustrates the importance of such GA-Bayesian approach applied in pipeline for fMRI data analysis.
|Number of pages||6|
|Publication status||Published - 2014 Jan 1|
|Event||2014 4th IEEE International Advance Computing Conference, IACC 2014 - Gurgaon, India|
Duration: 2014 Feb 21 → 2014 Feb 22
|Other||2014 4th IEEE International Advance Computing Conference, IACC 2014|
|Period||14/2/21 → 14/2/22|
All Science Journal Classification (ASJC) codes