Adaptive segmentation of EEG records: a new approach to automatic EEG analysis

The first step in a procedure for automatic EEG analysis is to compress the incoming data into a manageable format while preserving the essential diagnostic information. In our approach we mimic the visual procedure of looking through the record for segments and events of particular interest. We assume that the EEG is composed of roughly stationary segments of variable length, possibly superposed by sharp transients. By using an autoregressive model we have developed a procedure to detect the segment boundaries and locate transients, and to represent the information in the segments in terms of a set of parameters specifying their power spectra. In this way, the time structure as well as the frequency content of the signal is preserved. Examples of segmentation and transient detection are shown for several EEG signals, and the quality of the representation is demonstrated by simulating the original signal from the parameters. Possible applications to practical EEG analysis are discussed.