Sleep stage study with wavelet time-frequency analysis

The EEG is a non-invasive technique to study the brain and very useful in sleep analysis. The classification of the sleep in stages was widely used, but has been limited by its coarse resolution. In this paper the wavelet time-frequency analysis is applied to 16 seconds long epochs of EEG recordings to provide localized time-frequency information. The sleep stage classification results of the experiments indicated that the method of wavelet time-frequency analysis was feasible.