Teager Energy Based Filter-Bank Cepstra in EEG Classification for Seizure Detection Using Radial Basis Function Neural Network

摘要: About 1–3% of the world population suffers from epilepsy. Epileptic seizures are abnormal sudden discharges in brain with signatures manifesting electroencephalograph (EEG) recordings by frequency changes and increased amplitudes. These changes, this work, captured through static dynamic features derived three Teager energy based filter-bank cepstra (TE-FB-CEPs). We compared performance linear, logarithmic, Mel scale TE-FB-CEPs using radial basis function neural network general epileptic seizure detection. The comparison is tried on eight different classification problems which encompass all possible discriminations medical field related to In a previous study, traditional cepstrum same database, we had found that composite vectors showed degraded however, irrespective scaling used, it maintain excellent overall accuracy problems.