Classification of human brain waves using self-organizing maps

This chapter presents a method for the classification of EEG spectra by means of Kohonen's self-organizing map. We use EEG data recorded by 19 electrodes (channels), sampled at 128 Hz. Data vectors are extracted at intervals of half a second with a duration of one second each, resulting in vectors overlapping half a second. Before the training of the map, the sample vectors were compressed by either the Fast-Fourier-Transform or the Wavelet-Transform. Data preprocessed by the Fourier-Transform result in short-time power spectra. These spectra are filtered by butterworth filters that meet the EEG frequency bands of the delta-, theta-, alpha-, beta- and gamma-rhythms. Data preprocessed by the Wavelet-Transform result in wavelet coefficients that are combined and averaged. The preprocessed vectors form "clusters" on the trained self-organizing map that are related to specific EEG patterns.