Epileptic seizureprediction based on Hilbert Huang Transform and Artificial Neural Networks

For a patient diagnosed with epilepsy, a neurological disorder that affects the patient only during a seizure, and the following short duration for some cases, it is important to predict a seizure before it happens. EEG signal processing plays an important role in detection and prediction of epileptic seizures. The aim of this study is to develop a patient specific seizure prediction method based on Hilbert-Huang Transform. In this method EEG signals are decomposed into Intrinsic Mode Functions and first six IMFs are used to obtain features for classification of preictal and interictal recordings employing Artificial Neural Networks. Proposed method was tested on Freiburg iEEG database. A total of 58 hours of preictal data, prior to 87 seizures, and 504 hours of interictal data were examined. Algorithm resulted in 93.1% sensitivity (81 of 87 seizures) and 0.71 FPs/h using 30 seconds EEG segment with 50% overlap.