Autoregressive spectral analysis and model order selection criteria for EEG signals

The advantages of autoregressive (AR) modelling over the classical Fourier transform methods have been centre staged in previous years. But a problem with the AR method lies with the appropriate model order selection. We address this problem by studying the performance of three different types of order selection criteria for AR models to represent electroencephalogram signals. We perform this by extracting the EEG signals for different mental tasks and obtaining the appropriate model order given by the different criteria. From this, we derive the spectral density function. Using the spectral values, we train a neural network and classify the tasks into their respective categories. In this way, we show the difference in the performance level of the different model order selection criteria for EEG signals