A novel time-varying modelling and signal processing approach for epileptic seizure detection and classification

Electroencephalogram (EEG) signal analysis plays an essential role in detecting and understanding epileptic seizures. It is known that seizure processes are nonlinear and nonstationary, discriminating between rhythmic discharges and dynamic change is a challenging task in EEG based seizure detection. In this paper, a new time-varying (TV) modeling framework, based on an autoregressive (AR) model structure, is proposed to characterize and analyze EEG signals. The TV parameters of the AR model are approximated through a multi-wavelet basis function expansion (MWBF) approach. An effective ultraregularized orthogonal forward regression (UROFR) algorithm is employed to significantly reduce and refine the resulting expanded model. Given a time-varying process, the proposed TVAR-MWBF-UROFR method can generate a parsimonious TVAR model, based on which a high-resolution power spectrum density (PSD) estimation can be obtained. Informative features are then defined and extracted from the PSD estimation. The TVAR-MWBF-UROFR method is applied to a number of real EEG datasets; features obtained from these datasets are then used for seizure detection and classification. To make the results more accurate and reliable, a PCA algorithm is adopted to select the optimal feature subset, and a Bayesian optimization technique based on the Gaussian process (GP) is performed to determine the coefficients associated with each of the classifiers. Experimental results of the proposed approach outperform the compared state-of-the-art classifiers on two benchmark datasets. Moreover, the results produced by the proposed time-frequency analysis scheme are more reliable for seizure detection based on the noisy EEG datasets used in our case studies.