Automatic epilepsy recognition with using HOS analysis of EEG signals

In this paper, a higher order spectra scheme is proposed for recognition of epilepsy states. Epilepsy is a brain disorder that is characterized by sudden and recurrent seizures. we known that higher order spectra contain information not present in the power spectrum. Normal, pre-ictal and ictal signals were classified using a poly-SVM classifier. We reached an average accuracy of 97.2% for the two categories of epilepsy states (Normal & Ictal). In this research, both qualitative and quantitative results are presented. We concluded that HOS analysis could be an accurate tool in the evaluation of epilepsy states

کلیدواژه ها:

Epilepsy ، EEG signals ، HOS ، Bispectrum ، Bicoherence