Automatic detection of sleep stages using the EEG

We present a method for the detection of sleep stages using the EEG (electroencephalogram). The method consists of four steps: segmentation; parameter extraction; cluster analysis; and classification. The parameters we compared were the parameters of Hjorth, the harmonic parameters and the relative band energy. For cluster analysis we used a modified version of the K-means algorithm. It is shown that the investigated parameters are capable of, extracting information from the EEG relevant for sleep stage scoring. Using the modified K-means algorithm it is possible to find ´similar´ segments and hence automate the detection of sleep stages. However, extra information, e.g. the ECG (electrocardiogram) or the EOG (electrooculogram), is probably necessary for a clear discrimination between the different sleep stages.