Predicting epileptic seizure from MRI using fast single shot proximal support vector machine

Epilepsy is a neurological condition that produces brief disturbances in the normal electrical functions of the brain and is characterized by intermittent abnormal firing of neurons in the brain. Magnetic Resonance Imaging (MRI) is an important method adopted in epilepsy diagnosis. The detection of the epileptic activity requires a time-consuming analysis of the entire MRI data by an expert. Hence there is a need to generate an efficient prediction model for making a correct diagnosis of epileptic seizure and accurate prediction of its type. This paper deals with modeling of epileptic seizure prediction as classification task and a kind of support vector machine namely fast single shot proximal support vector machine with vector output has been employed to solve multiclass classification problem. The efficiency in terms of prediction accuracy and time consumption in classifying the MRI images is reported.