Advertisement

Building Dependable EEG Classifiers for the Real World – It’s Not Just about the Hardware

  • Gene Davis
  • Djordje Popovic
  • Robin R. Johnson
  • Chris Berka
  • Mirko Mitrovic
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5638)

Abstract

One of the major deficiencies with the EEG-based classifiers used in today’s laboratory settings is that they are often ill suited for the real world. In many cases the classifiers that were painstakingly developed in the controlled laboratory environment become unreliable with increased mobility of the user. In addition to increased mobility, many real world scenarios impose constraints on data collection that cannot be accommodated by the lab-created classifier. Addressing these issues throughout the development process of EEG-based classifiers by building hardware, software, and algorithms intended for use in the real world should result in more dependable classifiers. With this approach we were able to collect and classify data on a research vessel at sea, in the desert by night, on dismounted soldiers in the training field, and everywhere between.

Keywords

Electroencephalogram (EEG) Mobile EEG Operational Neuroscience Engagement Workload Drowsiness 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Besserve, M., Jerbi, K., Laurent, F., et al.: Classification methods for ongoing EEG and MEG signals. Biological Research 40, 415–437 (2007)CrossRefPubMedGoogle Scholar
  2. 2.
    Gevins, A.S., Morgan, N.H.: Classifier-directed signal processing in brain research. IEEE Transactions on Biomedical Engineering 33, 1054–1068 (1986)CrossRefPubMedGoogle Scholar
  3. 3.
    Mirsky, A.F., Pragay, E.B.: The relation of EEG and performance in altered states of consciousness, vol. 45, pp. 514–534. Research Publications – Association for Research in Nervous and Mental Disease (1967)Google Scholar
  4. 4.
    Walter, D.O., Rhodes, J.M., Adey, W.R.: Discriminating among states of consciousness by EEG measurements: a study of four subjects. Electroencephalography and Clinical Neurophysiology 22, 22–29 (1967)CrossRefPubMedGoogle Scholar
  5. 5.
    Walter, D.O., Rhodes, J.M., Kado, R.T., Adey, W.R.: A normative library of the human EEG, assessed by computer analysis in relation to behavioral states. Electroencephalography and Clinical Neurophysiology 23, 87–88 (1967)PubMedGoogle Scholar
  6. 6.
    Berka, C., Davis, G., Johnson, R.J., et al.: Psychophysiological Profiles of Sleep Deprivation and Stress during Marine Corps Training. Sleep 30, A132 (2007)Google Scholar
  7. 7.
    Bodenstein, G., et al.: Computerized EEG pattern classification by adaptive segmentation and probability-density-function classification. Description of the method. Computers in Biology and Medicine 15, 297–313 (1985)CrossRefPubMedGoogle Scholar
  8. 8.
    Creutzfeldt, O.D., Bodenstein, G., Barlow, J.S.: Computerized EEG pattern classification by adaptive segmentation and probability density function classification. Clinical evaluation. Electroencephalography and Clinical Neurophysiology 60, 373–393 (1985)CrossRefPubMedGoogle Scholar
  9. 9.
    Kramer, A., Parasuraman, R.: Neuroergonomics: Application of Neuroscience to Human Factors. In: Caccioppo, J.T., Tassinary, L.G., Berntson, G.G. (eds.) Handbook of Psychophysiology. Cambridge University Press, New York (2005)Google Scholar
  10. 10.
    Parasuraman, R.: Neuroergonomics: Research and Practice. Theoretical Issues in Ergonomics Science 4, 5–20 (2003)CrossRefGoogle Scholar
  11. 11.
    Parasuraman, R.: Neuroergonomics: The Brain at Work. Oxford University Press, New York (2005)Google Scholar
  12. 12.
    Peltoranta, M., Pfurtscheller, G.: Neural network based classification of non-averaged event-related EEG responses. Medical and Biological Engineering and Computing 32, 189–196 (1994)CrossRefPubMedGoogle Scholar
  13. 13.
    Pojman, N., Johnson, R.J., Kintz, N., et al.: Assessing fatigue using EEG classification metrics during neurocognitive testing. In: 23rd Annual Meeting of the Associated Professional Sleep Societies, LLC, Seattle, WA (Submitted, 2009)Google Scholar
  14. 14.
    Wilson, G., Fisher, F.: Cognitive task classification based upon topographic EEG data. Biological Psychology 40, 239–250 (1995)CrossRefPubMedGoogle Scholar
  15. 15.
    Berka, C., Johnson, R., Whitmoyer, M., et al.: Biomarkers for Effects of Fatigue and Stress on Performance: EEG, P300 and Heart Rate Variability. Human Factors and Ergonomics Society, New York (2008)Google Scholar
  16. 16.
    Berka, C., Levendowski, D., Cvetinovic, M., et al.: Real-time Analysis of EEG Indices of Alertness, Cognition, and Memory Acquired with a Wireless EEG Headset. International Journal of Human-Computer Interaction 17, 151–170 (2004)CrossRefGoogle Scholar
  17. 17.
    Berka, C., Levendowski, D., Davis, G., et al.: Nicotine Administration and Withdrawal Effects on EEG metrics of Attention, Memory and Workload: Implications for Cognitive Resource Allocation. In: Schmorrow, D., Stanney, K., Reeves, L. (eds.) Augmented Cognition: Past, Present and Future, Foundations of Augmented Cognition, pp. 174–183. Strategic Analysis, Inc., Arlington (2006)Google Scholar
  18. 18.
    Berka, C., Levendowski, D., Konstantinovic, Z.R., et al.: Detection of drowsiness with realtime analysis of the electroencephalogram (EEG). In: National Institutes of Health SBIR Conference, Bethesda, MD (2000)Google Scholar
  19. 19.
    Berka, C., Levendowski, D., Ramsey, C.K., et al.: Evaluation of an EEG-Workload Model in an Aegis Simulation Environment. In: Caldwell, J.A., Wesensten, N.J. (eds.) Proceedings of SPIE Defense and Security Symposium, Biomonitoring for Physiological and Cognitive Performance during Military Operations, vol. 5797, pp. 90–99. SPIE: The International Society for Optical Engineering, Orlando, FL (2005)Google Scholar
  20. 20.
    Berka, C., Levendowski, D., Westbrook, P., Davis, G., Lumicao, M., Olmstead, R., Popovic, M.V., Zivkovic, V., Ramsey, C.: EEG Quantification of Alertness: Methods for Early Identification of Individuals Most Susceptible to Sleep Deprivation. In: Caldwell, J.A., Wesensten, N.J. (eds.) Proceedings of SPIE Defense and Security Symposium, Biomonitoring for Physiological and Cognitive Performance during Military Operations, vol. 5797, pp. 78–89. SPIE: The International Society for Optical Engineering, Orlando, FL (2005b)CrossRefGoogle Scholar
  21. 21.
    Berka, C., Levendowski, D.J., Konstantinovic, Z.R., et al.: Detection of electroencephalographic indices of drowsiness in realtime using a multi-level discriminant function analysis. Sleep 23, A243–A244 (2000)Google Scholar
  22. 22.
    Berka, C., Levendowski, D.J., Lumicao, M.N., et al.: EEG correlates of task engagement and mental workload in vigilance, learning, and memory tasks. Aviation, Space and Environmental Medicine 78, B231–B244 (2007)Google Scholar
  23. 23.
    Mitler, M.M., Westbrook, P., Levendowski, D.J., et al.: Validation of automated EEG quantification of alertness: methods for early identification of individuals most susceptible to sleep deprivation. Sleep 25, A147–A148 (2002)Google Scholar
  24. 24.
    Westbrook, P., Berka, C., Levendowski, D., et al.: Quantification of Alertness, Memory and Neurophysiological Changes in Sleep Apnea Patients Following Treatment with nCPAP. Sleep 27, A223 (2004)Google Scholar
  25. 25.
    Westbrook, P., Berka, C., Levendowski, D.J., et al.: Biobehavioral quantification of alertness and memory in patients with sleep apnea. Sleep 25, A49–A50 (2002)Google Scholar
  26. 26.
    Craven, P.L., Belov, N., Tremoulet, P., et al.: Cognitive Workload Gauge Development: Comparison of Real-time Classification Methods. In: Schmorrow, D., Stanney, K., Reeves, L. (eds.) Augmented Cognition: Past, Present and Future, Foundations of Augmented Cognition, pp. 66–74. Strategic Analysis, Inc., Arlington (2006)Google Scholar
  27. 27.
    Poythress, M., Russell, C., Siegel, S., et al.: Correlation between Expected Workload and EEG Indices of Cognitive Workload and Task Engagement. In: Augmented Cognition 2006 Conference (2006)Google Scholar
  28. 28.
    Poythress, M., Russell, C., Siegel, S., et al.: Correlation between Expected Workload and EEG Indices of Cognitive Workload and Task Engagement. In: Schmorrow, D., Stanney, K., Reeves, L. (eds.) Augmented Cognition: Past, Present and Future, Foundations of Augmented Cognition, pp. 32–44. Strategic Analysis, Inc., Arlington (2006)Google Scholar
  29. 29.
    Stevens, R., Galloway, T., Berka, C.: Allocation of Time, EEG-Engagement and EEG-Workload Resources as Scientific Problem Solving Skills are Acquired in the Classroom. In: Augmented Cognition 2007 Conference (2007)Google Scholar
  30. 30.
    Stevens, R., Galloway, T., Berka, C.: EEG-Related Changes in Cognitive Workload, Engagement and Distraction as Students Acquire Problem Solving Skills. In: The User Modeling Conference, Athens, Greece (2007)Google Scholar
  31. 31.
    Dickson, B.T.: The Cognitive Cockpit - a test-bed for Augmented Cognition. In: 1st International Conference on Augmented Cognition, Las Vegas, NV (2005)Google Scholar
  32. 32.
    Kinces, W.E.: DaimlerChrysler’s closed loop integrated prototype: Current status and outlook. In: 1st Augmented Cognition International, Las Vegas, NV (2005)Google Scholar
  33. 33.
    Ververs, P.M., Whitlow, S., Dorneich, M., Mathan, S.: Building Honeywell’s Adaptive System for the Augmented Cognition Program. In: 1st International Conference on Augmented Cognition, Las Vegas, NV (2005)Google Scholar
  34. 34.
    Mathan, S., Whitlow, S., Dorneich, M., Ververs, P., Davis, G.: Neurophysiological Estimation of Interruptibility: Demonstrating Feasibility in a Field Context. In: Augmented Cognition 2007 Conference (2007)Google Scholar
  35. 35.
    Berger, H.: Uber das Elektroenzephalorgam des Menschen. Arch Psychiatr. Nervenk 90, 527–570 (1929)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Gene Davis
    • 1
  • Djordje Popovic
    • 1
    • 2
  • Robin R. Johnson
    • 1
  • Chris Berka
    • 1
  • Mirko Mitrovic
    • 1
  1. 1.Advanced Brain Monitoring, Inc.CarlsbadUSA
  2. 2.University of Southern CaliforniaLos AngelesUSA

Personalised recommendations