Sparse ICA based on infinite norm for fMRI analysis

Abstract

Functional MRI (fMRI) is a functional neuroimaging technique that measures the brain activity by detecting the associated changes in blood flow. Independent component analysis (ICA) provides a feasible approach to analyze the collected data sets. In this paper, we introduce a novel criterion via infinity norm to achieve the sparse solution. The experimental result has been shown that the approach can be successfully applied in fMRI data. In memory-imagine cognitive experiment, the activated regions for different tasks are different in brain. But some regions are activated in each runs, which suggests that these brain regions may play an important role in cognition functions of memory-imagine.