Epileptic seizure prediction using angle method

Epileptic seizures are generated by abnormal activity of neurons. The prediction of epileptic seizures is an important issue in neurology field, since it may improve the quality of patient's life suffering from epilepsy. In this study, we present angle method, which can be used for extracting behavior of trajectories in phase space. This method focuses on angles between difference of state vectors and by simple statistical operations three features are extracted. Applying to the Freiburg EEG dataset, it is found that the method is able to detect the behavioral changes of the neural activity prior to epileptic seizures, so it can be used for epileptic seizure prediction. Performance assessment of the proposed method shows its superior efficiency in comparison with many other methods.