International Journal of Computational
Intelligence Research (IJCIR)
Volume 3, Number 1 (2007)
Estimation of motor imaginary using fMRI experiment based EEG sensor location
Sang Han Choi
School of Electrical Engineering and Computer Science, Kyungpook National University 1370 Sankyuk-Dong, Puk-Gu, Taegu 702–701, Korea.
Department of Brain and Cognitive Science, Massachusetts Institute of Technology 77 Massachusetts Avenue, Cambridge, MA 02139, USA
Brain computer interface (BCI) is based on brain activity. It controls a computer system by imagination or other mental activities. In order to improve the performance of the BCI system based on the scalp EEG, it is critical to get reliable EEG signals. In addition, it is important to minimize the noise and artifacts from EEG signals. In this paper, we focus on minimizing the artifacts besides maximizing brain activity information that is related with mental tasks obtained from EEG signals. To make EEG signals more informative, it is necessary to consider suitable mental tasks and the location of the EEG sensor. Using fMRI experiments, we found that the supplementary motor area (SMA) is activated whenever mental tasks include the imaginary of body movements. Based on this observation, we implement a primitive type of EEG based brain computer interface using linear discriminant analysis (LDA).
BCI, EEG, fMRI, SMA, LDA.