A Hybrid Approach Based on Higher Order Spectra for Clinical Recognition of Seizure and Epilepsy Using Brain Activity

This paper proposes a reliable and efficient technique to recognize different epilepsy states, including healthy, interictal, and ictal states, using Electroencephalogram (EEG) signals.
The proposed approach consists of pre-processing, feature extraction by higher order spectra, feature normalization, feature selection by genetic algorithm and ranking method, and classification by support vector machine with Gaussian and polynomial radial basis function kernels. The proposed approach is validated on a public benchmark dataset to compare it with previous studies.
The results indicate that the combined use of above elements can effectively decipher the cognitive process of epilepsy and seizure recognition. There are several bispectrum and bicoherence peaks at every bi-frequency plane, which reveal the location of the quadratic phase coupling. The proposed approach can reach, in almost all of the experiments, up to 100% performance in terms of sensitivity, specificity, and accuracy.
Comparing between the obtained results and previous approaches approves the effectiveness of the proposed approach for seizure and epilepsy recognition.