A new algorithm for automatic identification of spike-wave EEG signals in epileptic patient-specific

"Appropriate diagnosis and treatment of epilepsy is a main public health issue. Patients suffering from this disease often exhibit different physical characterizations, which results from the synchronous and excessive discharge of a group of neurons in the cerebral cortex. Extracting this information using EEG signals is an important problem in biomedical processing. In this work we propose a new method to indentify and characterize patient specific spike-and-wave EEG epileptic signals. The method is based on the use of trained neuronal networks on probability density function parameters of the translation and rescaling of the Student'st-distribution (location: µ,scale: σ and shape: ν) of pure spike-and-wave-signals. The neuronal network was trained with both normal and epileptic signals. The study resulted in 100% specificity and sensitivity on the studied signals."