Event Abstract Back to Event EEG indices of drowsiness and monotonous operator work Olga Tkachenko1* and Alexander Frolov1 1 IHNA RAS, Russia Since monotonous operator work is widespread, the task of online alertness and drowsiness control is undoubtedly actual task nowadays. There are several physiological indices of drowsy state, but EEG is one of the few that show really good correlation with alertness level and early stages of drowsiness. With widening of informational technologies and investigation of wireless electrodes it is possible to use some complicated mathematical methods for real-time monitoring of operator state.In our experiments sleep-deprived subjects were instructed to drive the simple car simulator pending 1.5 hours. EEG from two parietal and two occipital electrodes was registered, as well as car simulator parameters and video of subject’s face. Car declination from the center of the road and video of subject’s face were then used as independent indices of drowsiness and were compared with EEG-based classification.Twenty volunteers between 18 and 25 years old took part in the experiment. Each of them was first tested in control experiment with no sleep deprivation and later – after sleep deprivation. Seven subjects showed high drowsiness level in experiment with sleep deprivation and were chosen for detailed analysis. We have compared several classification methods, such as Tietze method based on alpha spindles parameters, common spatial pattern method used in EEG-based brain-computer interfaces, non-parametric Bayesian method and two-level non-linear perceptron. EEG was filtered in alpha range (7-15 Hz) and 10-second intervals were chosen for classification with each of methods listed above. It was shown that all these methods show good correlation with one another, but classification based on relatively new in this field common spatial pattern and two-level perceptron showed much better correlation (correlation coefficient of the order of 0.8-0.9) with expert drowsiness scoring than Tietze method that was used for this purposes before. Conference: Neuroinformatics 2009, Pilsen, Czechia, 6 Sep - 8 Sep, 2009. Presentation Type: Poster Presentation Topic: Electrophysiology Citation: Tkachenko O and Frolov A (2019). EEG indices of drowsiness and monotonous operator work. Front. Neuroinform. Conference Abstract: Neuroinformatics 2009. doi: 10.3389/conf.neuro.11.2009.08.067 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 22 May 2009; Published Online: 09 May 2019. * Correspondence: Olga Tkachenko, IHNA RAS, St.Petersburg, Russia, tkachenkoon@gmail.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Olga Tkachenko Alexander Frolov Google Olga Tkachenko Alexander Frolov Google Scholar Olga Tkachenko Alexander Frolov PubMed Olga Tkachenko Alexander Frolov Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.