Binary Neural Classifier of Raw EEG Data to Separate Spike and Sharp Wave of the Eye Blink Artifact

This work presents the study, the development and the evaluation of a binary neural classifier to separate the epileptiform events (spike and sharp wave) and eye blink artifacts in electroencephalography exams (EEG). The eye blink is the main artifact that affects the performance of the automatic systems for identification of epileptiform events in EEG signals. The methodology for the development of the binary neural classifier through an ANN MLP is approached. The performance evaluation of the classifier is realized through the statistic index, performance index and ROC curve with performance criterion. With the EER criterion was obtained sensitivity of 85.9%, specificity of 87.1%, positive selectivity of 86.7% and negative selectivity of 86.3%.