Monitoring drowsiness on-line using a single encephalographic channel

Antoine Picot (1) , Sylvie Charbonnier (1) , Alice Caplier (2)

1 GIPSA-SA-IGA - GIPSA - Signal et Automatique pour le Diagnostic et la Surveillance
2 GIPSA-GPIG - GIPSA - Géométrie, Perception, Images, Geste

In this paper, an on-line drowsiness detection algorithm using a single electroencephalographic (EEG) channel is presented. This algorithm is based on a means comparison test to detect changes of the alpha relative power ([8-12]Hz band) and the beta relative power ([12-20]Hz band). The detection on these two bands are then merged using fuzzy logic. The main advantage of the method proposed is that the detection threshold is completely independent of drivers and does not need to be tuned for each person. An artefact detection is also processed on the EEG signal to avoid false detection. This algorithm, which works on-line, has been tested on a huge dataset representing 60 hours of driving and give good results with nearly 85% of good detections and 20% of false alarms.

Mots clés: Biomedical signal processing (EEG); Diagnostic without model; artefact detection; fuzzy logic

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Antoine Picot, Sylvie Charbonnier, Alice Caplier. Monitoring drowsiness on-line using a single encephalographic channel. ISBN 978-953-307-013-1. Recent Advances in Biomedical Engineering, Carlo Alexandre Barros de Mello, pp.145-164, 2009, In-Tech. ⟨hal-00449292⟩