An algorithm for detecting events in video EEG monitoring data of patients with craniocerebral injuries

One of the problems solved by analyzing data long-term Video EEG monitoring is differentiation epileptic and artifact events. For this, not only multichannel signals are used, but also video analysis, since traditional methods based on analysis wavelet spectrograms cannot reliably distinguish an seizure from a chewing artifact. In this paper, we propose algorithm for detecting events joint level optical flow ridges spectrograms. The preliminary results real clinical given. show possibility in principle reliable distinguishing non-epileptic seizures.