Title :
Discriminating mental tasks using EEG represented by AR models
Author :
Anderson, Charles W. ; Stolz, Erik A. ; Shamsunder, Sanyogita
Author_Institution :
Dept. of Comput. Sci., Colorado State Univ., Fort Collins, CO, USA
Abstract :
EEG signals are modeled using single-channel and multi-channel autoregressive (AR) techniques. The coefficients of these models are used to classify EEG data into one of two classes corresponding to the mental task the subjects are performing. A neural network is trained to perform the classification. When applying a trained network to test data, the authors find that the multivariate AR representation performs slightly better, resulting in an average classification accuracy of about 91%
Keywords :
electroencephalography; medical signal processing; neural nets; physiological models; EEG data classification; EEG models; classification accuracy; electrodiagnostics; mental tasks discrimination; multi-channel autoregressive techniques; single-channel autoregressive techniques; Biological neural networks; Brain modeling; Electrodes; Electroencephalography; Neural networks; Performance evaluation; Psychology; Signal representations; Smoothing methods; Testing;
Conference_Titel :
Engineering in Medicine and Biology Society, 1995., IEEE 17th Annual Conference
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2475-7
DOI :
10.1109/IEMBS.1995.579248
