About this document

Automatic EEG Drowsiness Detection by Ikram Tenani is a document available to read on EtoBox.

This technical note describes an automatic method to detect drowsiness in EEG records using multimodal analysis. 19 features were computed from a single EEG channel to differentiate alert and drowsy states. After feature selection, 7 parameters were chosen as inputs for a neural network classifier. The method achieved 87.4% and 83.6% correct detection rates for alertness and drowsiness, respectively. The easy to compute features could be used in an automatic drowsiness detection system for vehicles to help

Author

Ikram Tenani

Language

EN