general linear model estimation in fMRI using genetic algorithm in the frequency domain

funtional magnetic resonance imaging fMRI has been shown to be useful in the detection of the brain activity . This work deals with the parameter estimation problem of the linear model for fMRI time seies contaminated by fractional -integrated processes and white noise the adopted maximum likelihood ML method is highly nonlinear estimation problem. since the genetic algorithm GA tends to find the global solution. an estimation scheme based on the GA is developed to solve the ML parameter estimation problem.

Keywords:

fMRI , genetic algorithm , fractal noise , estimation