Advertisement

“What Was He Thinking?”: Using EEG Data to Facilitate the Interpretation of Performance Patterns

  • Gwendolyn E. Campbell
  • Christine L. Belz
  • Phan Luu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5638)

Abstract

Previous research has demonstrated that EEG data can be used to identify and remove unintentional responses from a data set (guesses and slips). This study sought to determine if removing this error variance has a significant impact on the interpretation of a trainee’s performance. Participants were taught to recognize tank silhouettes. Multiple linear regression models were built for each participant based on three sets of their data: 1) all trials of their performance data, 2) only trials that were learned according to a state space analysis, and 3) their intentional data as identified by EEG. When compared to an expert model, each of the three models for every participant yielded a different diagnosis, indicating that filtering performance data with EEG data changes the interpretation of a participant’s competence.

Keywords

electroencephalography training student modeling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Berka, C., Levendowski, D., Ramsey, C., Davis, G., Lumicao, M., Stanney, K., Reeves, L., Regli, S., Tremoulet, P., Stibler, K.: Biomonitoring for Physiological and Cognitive Performance during Military Operations. In: Caldwell, J.A., Wesensten, N.J. (eds.) Proceedings of the SPIE, vol. 5797, pp. 90–99 (2005)Google Scholar
  2. 2.
    Dickson, B., Belyavin, A.: The use of electrophysiological markers of expertise to configure adaptive training systems. In: Schmorrow, D., Nicholson, D., Drexler, J., Reeves, L. (eds.) Foundations of Augmented Cognition, 4th edn., pp. 138–144. Strategic Analysis, Inc. and the Augmented Cognition International Society, Arlington (2007)Google Scholar
  3. 3.
    DuRousseau, D.R., Mannucci, M.A., Stanley, J.P.: Will augmented cognition improve training results? In: Schmorrow, D. (ed.) Foundations of Augmented Cognition, vol. 2, pp. 956–963. Lawrence Erlbaum & Associates Inc., Mahwah (2005)Google Scholar
  4. 4.
    Luu, P., Campbell, G.E.: “Oops, I did it again”: Using neurophysiological indicators to distinguish slips from mistakes in simulation-based training systems. In: Schmorrow, D. (ed.) Foundations of Augmented Cognition, vol. 2, pp. 941–945. Lawrence Erlbaum Associates Publishers, Mahwah (2005)Google Scholar
  5. 5.
    Campbell, G.E., Luu, P.: A preliminary comparison of statistical and neurophysiological techniques to assess the reliability of performance data. In: Schmorrow, D., Nicholson, D., Drexler, J., Reeves, L. (eds.) Foundations of Augmented Cognition, 4th edn., pp. 119–127. Strategic Analysis, Inc., Arlington (2007)Google Scholar
  6. 6.
    Campbell, G.E., Buff, W.L., Bolton, A.E.: Viewing training through a fuzzy lens. In: Kirlik, A. (ed.) Adaptation in Human-Technology Interaction: Methods, Models and Measures, pp. 149–162. Oxford University Press, Oxford (2006)Google Scholar
  7. 7.
    Smith, A.C., Frank, L.M., Wirth, S., Yanike, M., Hu, D., Kubota, Y., Graybiel, A.M., Suzuki, W.A., Brown, E.N.: Dynamic analysis of learning in behavioral experiments. The Journal of Neuroscience 24(2), 447–461 (2004)CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Gwendolyn E. Campbell
    • 1
  • Christine L. Belz
    • 1
  • Phan Luu
    • 2
  1. 1.Naval Air Warfare Center Training Systems DivisionOrlandoUSA
  2. 2.Electrical Geodesics, Inc., Riverfront Research ParkEugeneUSA

Personalised recommendations