Alaa Eldeen Mahmoud Helal Helal
Helwan University, Egypt
Title: Automatic detection of epileptic discharges in long EEG recordings
Biography
Biography: Alaa Eldeen Mahmoud Helal Helal
Abstract
Electroencephalogram (EEG) is a representative signal containing information about the cerebral cortex activities, has
been the most utilized tool to clinically assess brain functioning and the diagnosis of epilepsy. EEG morphology is
characterized by short transients and sudden waveform changes. Investigation of these rapid events is still done manually
through neurophysiologists by his/her naked eye to identify all occurrences of these electrographic abnormalities which is very
hard and may be impossible, especially with the presence of a lot of many artifacts. Because of that, automatic EEG detection
techniques have received intense attention since it aid for rapid identification of neurological abnormalities and opening a
window to analyze the mechanisms of epilepsy. The nonlinearity nature and fast transitions between non-seizure, pre-seizure,
and seizure states guide us to a promising solution in this work by combining several processing techniques to capture the
EEG features in multiple domains. The method was tested on real epileptic EEG data, giving very promising results that
allow it to offer better capabilities for assisting clinical neurophysiologists in routine EEG examinations for epilepsy diagnosis,
nominating it to find its way into routine clinical use for other neurological disorders. For its fast computation, it provides a
novel wide window for online processing of EEG data. Also, it can play a positive role for further research and applications
in cerebral activity as deep brain and vagus nerve stimulation for seizure prevention on-line by closed feedback loop system