Epileptic Seizure Classification based on Supervised Learning Models

This paper presents several aspects concerning epileptic seizures detection by EEG signal classification based on supervised learning models with associated learning algorithms that analyze data. In order to detect epileptic seizures has been used to support vector machine model. Support Vector Machine (SVM) is a classifier formally defined by a separating hyperplane being based on training data (supervised learning) and the algorithm outputs representing the optimal hyperplane. The adopted approach was to extract features from the data in order to be used to train and test data by using machine learning models in MATLAB. Seizures signals were obtained from EEG recordings from pediatric subjects with intractable seizures and ages 3-22 years.