Inspection of EEG signals for efficient seizure prediction

Abstract Epilepsy seizure prediction has become one of the interesting fields that attract researchers to innovate solutions. For epilepsy patients, Electroencephalography (EEG) signals consist of three activities: normal, pre-ictal and ictal. In order to design a prediction model for the ictal state, it is required to distinguish between the activities of EEG signals. This paper presents efficient seizure prediction approaches from EEG signals based on statistical analysis, digital band-limiting filters and artificial intelligence. Band-limiting filters are used to remove out-of-band noise and spurious effects. Then, statistical analysis is adopted for channel selection and seizure prediction based on a thresholding strategy. This statistical analysis depends on amplitude, median, mean, variance and derivative of the EEG signal. The adopted band-limiting filter affects the seizure prediction metrics such as accuracy, prediction time and false alarm rate. The prediction process consists of two phases: training and testing. Both k-means clustering and Multi-Layer Perceptron (MLP) networks are considered for seizure prediction based on artificial intelligence. The proposed approaches can be implemented in a mobile application to give alerts to patients or care givers. The simulation results reveal that the proposed approaches present high performance in terms of accuracy, prediction time and false alarm rate.