Nonlinear considerations in EEG signal classification

We investigate the effect of incorporating modeling of nonlinearity on the classification of electroencephalogram (EEG) signals using an artificial neural network (ANN). It is observed that the ANN's predictive ability is improved after preprocessing EEG signals using a particular nonlinear modeling technique, viz. a bilinear model, compared with those obtained by using a particular classical linear analysis method, viz. an autoregressive (AR) model. Until recently, linear time-invariant Gaussian modeling has dominated the development of time series modeling and feature extraction. The advantage of such classical models lies in the fact that a complete signal processing theory is available. In the case of EEG signals, where the underlying theory regarding the dynamical law governing the generation of these signals (e,g., the underlying physiological factors) is not completely understood, a case can be made for using improved signal processing models that are not subject to linear constraints. Such models should recognize important features of the observed data that may not be well modeled by a linear time-invariant model. It is known that EEG signals are nonstationary, and it is possible that they may be nonlinear as well. Thus, one way of gaining further insights on the structure of EEG signals is to introduce nonlinear models and higher order spectra. This paper compares the results of classification using a linear AR model with those obtained from a bilinear model. It is shown that in certain cases, the nonlinearity of the EEG signals is an important factor that ought to be taken into consideration during preprocessing of the signals prior to the classification task.