Bilkent University
Department of Computer Engineering

---

CS 590 SEMINAR

 

Epileptic seizure detection

 

Elmira Khajei
MS Student
Computer Engineering Department
Bilkent University

Epilepsy is one of the most common neurologic disorders in the world. It is associated with recurrent, unprovoked epileptic seizures. The electroencephalogram (EEG) signal is the most prominent means to study epilepsy and capture changes in electrical brain activity that could indicate a seizure. This work presents an adaptive patient-specific seizure detection framework where first, EEG signals are segmented into 5 second long segments followed by extraction of a wide range of features, including time and frequency domain features, cross-correlation and graph theoretic features between EEG channels. An SVM classifier is used to classify seizure and non-seizure EEG signal segments. The evaluation is performed using long-term EEG recordings from the open CHB-MIT scalp EEG database.

 

DATE: 09 December 2019, Monday @ 17:10
PLACE: EA-409