Sleep stage classification based on Hjorth descriptors of EEG signals

This bachelor thesis is focused on the distinction between sleep stages from EEG signals. In its first part the classical method of visual classification of sleep stages is introduced, the second part introduces an automated method for sleep stage scoring. It is a method that uses the three parameters of Hjorth to create a vector space, in which, on the basis of similarity of formed shapes, different stages of sleep could be distinguished. Parameters of Hjorth are calculated from the whole EEG signal, and also from its bands. In the next section of this thesis a principle component analysis is performed. The principle components are placed into a vector space analogously with parameters of Hjorth and the character of formed objects is observed