Multivariate Autoregressive Models for Classification of Spontaneous Electroencephalogram During Mental Tasks1

This article explores the use of scalar and multivariate autoregressive (AR) models to extract features from the human electroencephalogram (EEG) with which mental tasks can be discriminated. This is part of a larger project to investigate the feasibility of using EEG to allow paralyzed persons to control a device like a wheelchair. EEG signals from four subjects were recorded while they performed two mental tasks. Quarter-second windows of 6-channel EEG were transformed into four different representations: scalar AR model coefficients, multivariate AR coefficients, eigenvalues of a correlation matrix, and the Karhunen-Loève transform of the multivariate AR coefficients. Feature vectors defined by these representations were classified with a standard, feedforward neural network trained via the error backpropagation algorithm. The four representations produced similar results, with the multivariate AR coefficients performing slightly better and more consistently with an average classification accuracy of 91.4% on novel, untrained, EEG signals. 1Please send all correspondence to Charles Anderson. This work was supported by the National Science Foundation through grant IRI-9202100.