Single feature-based non-convulsive epileptic seizure detection using multi-class SVM

Epileptic seizures are abnormal, excessive, synchronous and unprovoked neural activity occuring in the brain affecting 2% of the world population. Epileptic patients mostly generates interictal EEG which on accurate detection provides vital information for epileptic seizure prediction. Nonconvulsive epilepsy, most commonly occuring epilepsy, results in continuous seizing of brain and the patient becomes unresponsive during the episode. This type of epileptic seizures show minimal symptoms and are often under-diagnosed resulting in late treatment. A multi level classification (epileptic, interictal and normal) providing interictal information in addition to normal and epileptic informations proves to be highly useful to Neurologists in the prediction and diagnosis of nonconvulsive epileptic seizures. An automated multilevel SVM based nonconvulsive epileptic seizure detection method utilizing a single feature vector (enabling fast classification) calculated from the fifth detail wavelet coefficients of the given EEG data is proposed here. Case study on different features like energy, mean energy, entropy, mean cross correlation, mean curve length, coefficient of variation, interquartile range and median absolute deviation yielded an optimum single feature. Energy, entropy, interquartile range and median absolute deviation were effective (above 95% accuracy) for the multi-level classification of EEG data with interquartile range being optimum feature with 99.96% accuracy and very low runtime of less than six seconds.