Patient Specific Seizure Prediction System Using Hilbert Spectrum and Bayesian Networks Classifiers

<table>An example of postprocessing procedure shown for 3rd seizure of patient 16. Upper row shows the probability of having a seizure in near future obtained every 15 seconds (red rectangles show 5-minute windows). Lower row shows the mean probabilities of having a preictal state in 5-minute time intervals.</table>

Computational and Mathematical Methods in Medicine

fig4

Figure 4

Figure 4: Patient Specific Seizure Prediction System Using Hilbert Spectrum and Bayesian Networks Classifiers 