Classification of Cognitive States using Task-Specific Connectivity Features

Human brain activity maps are produced by functional MRI (fMRI) research that describes the average level of engagement during a specific task various regions. Functional connectivity interrelationship, integrated performance, and organization these different This study investigates to quantify interactions between regions engaged concurrently in task. The key focus this was introduce demonstrate task-specific among using fMRI data decode cognitive states proposing novel classifier features. Two models were considered: graph-based Granger causality-transfer entropy framework. Connectivity strengths obtained used for state classification. parameters nodal global graph analysis from framework considered, transfer values causal model considered as features proposed achieved an accuracy 95% on StarPlus dataset showed improvement 5% compared existing Tensor-SVD classification algorithm.