Detection of seizures in EEG signal using weighted locally linear embedding and SVM classifier

To diagnose the structural disorders of brain, electroencephalography (EEG) is routinely used for observing the epileptic seizures in neurology clinics, which is one of the major brain disorders till today. In this work, we present a new, EEG-based, brain-state identification method which could form the basis for detecting epileptic seizure. We aim to classify the EEG signals and diagnose the epileptic seizures directly by using weighted locally linear embedding (WLLE) and support vector machine (SVM). Firstly, we use WLLE to do feature extraction of the EEG signal to obtain more compact representations of the internal characteristic and structure in the original data, which captures the information necessary for further manipulations. Then, SVM classifier is used to identify the seizures onset state from normal state of the patients.