Efficient Epileptic Seizure Prediction Approach Based on Hilbert Transform

This paper introduces a patient-specific method for seizure prediction applied to scalp Electroencephalography (sEEG) signals. The proposed method depends on computing the instantaneous amplitude of the analytic signal by applying Hilbert transform on EEG signals. Then, the Probability Density Functions (PDFs) are estimated for amplitude, local mean, local variance, derivative and median as major features. This is followed by a threshold-based classifier which discriminates between pre-ictal and inter-ictal periods. The proposed approach utilizes an adaptive algorithm for channel selection to identify the optimum number of needed channels which is useful for real-time applications. It is applied to all patients from the CHB-MIT database, achieving an average prediction rate of 96.46%, an average false alarm rate of 0.028077/h and an average prediction time of 60.1595 minutes using a 90-minute prediction horizon. Experimental results prove that Hilbert transform is more efficient for prediction than other existing approaches.