A novel method of EEG data acquisition, feature extraction and feature space creation for early detection of epileptic seizures

In this paper we describe a simple and very fast method of data acquisition, feature extraction and feature space creation for epileptic seizure detection. The scalp electroencephalogram (EEG) dataset [1, 2] collected at the Children's Hospital Boston from 22 pediatric patients having 192 intractable seizures (available as CHB-MIT database) is used to assess this simple approach against existing ones [1, 3], with very positive results reaching up to 99.48% Sensitivity.