EEG-based drivers' drowsiness monitoring using a hierarchical Gaussian mixture model

Authors:
Roman Rosipal;Björn Peters;Göran Kecklund;Torbjörn Åkerstedt;Georg Gruber;Michael Woertz;Peter Anderer;Georg Dorffner
Affiliations:
Austrian Research Institute for Artificial Intelligence, Vienna, Austria;Swedish National Road and Transport Research Institute, Linköping, Sweden;Karolinska Institutet, Stockholm, Sweden;Karolinska Institutet, Stockholm, Sweden;The Siesta Group Schlafanalyse GmbH, Vienna, Austria;Austrian Research Institute for Artificial Intelligence, Vienna, Austria;The Siesta Group Schlafanalyse GmbH, Vienna, Austria and Department of Psychiatry and Psychotherapy, Medical University of Vienna, Vienna, Austria;Austrian Res. Institute for Artificial Int., Vienna, Austria and The Siesta Group Schlafanalyse GmbH, Vienna, Austria and Inst. of Medical Cybernetics and Artificial Int., Center for Brain Res., M ...
Venue:
FAC'07 Proceedings of the 3rd international conference on Foundations of augmented cognition
Year:
2007

Citing 1
Cited 4

Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)

Enabling cognitive load-aware AR with rateless coding on a wearable network

Advances in Multimedia
An integrated hierarchical gaussian mixture model to estimate vigilance level based on EEG recordings

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Hybrid computer vision system for drivers' eye recognition and fatigue monitoring

Neurocomputing
An integrated Gaussian mixture model to estimate vigilance level based on EEG recordings

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We developed an EEG-based probabilistic model, which effectively predicts drowsiness levels of thirty-two subjects involved in a moving base driving simulator experiment. A hierarchical Gaussian mixture model (hGMM) with two mixture components at the lower hierarchical level is used. Each mixture models data density distribution of one of the two drowsiness cornerstones/classes represented by 4-second long EEG segments with low and high drowsiness levels. We transfer spectral contents of each EEG segment into a compact form of autoregressive model coefficients. The Karolinska drowsiness scoring method is used to initially label data belonging to individual classes. We demonstrate good agreement between Karolinska drowsiness scores and the predicted drowsiness, when the hGMM is applied to continuously monitor drowsiness over the time-course of driving sessions. The computations associated with the approach are fast enough to build up a practical real-time drowsiness monitoring system.