Identifying mental tasks from spontaneous EEG: Signal representation and spatial analysis

  • Charles W. Anderson
Bio-inspired Systems
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1607)


Feedforward neural networks are trained to classify half-second segments of six-channel, EEG data into one of five classes corresponding to five mental tasks performed by one subject. Two and three-layer neural networks are trained on a 128-processor SIMD computer using 10-fold cross-validation and early stopping to limit over-fitting. Four representations of the EEG signals, based on autoregressive (AR) models and Fourier Transforms, are compared. Using the AR representation and averaging over consecutive segments, an average of 72% of the test segments are correctly classified; for some test sets 100% are correctly classified. Cluster arm, is of the resulting hidden-unit weight vectors suggests which electrodes and representation components are the most relevant to the classification problem.


electroencephalogram pattern recognition autoregressive models brain-computer interface 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    C. W. Anderson, S. V. Devulapalli, and E. A. Stolz. Determining mental state from EEG signals using neural networks. Scientific Programming, 4(3):171–183, Fall 1995.Google Scholar
  2. 2.
    C. W. Anderson, S. V. Devulapalli, and E. A. Stolz. EEG signal classification with different signal representations. In F. Girosi, J. Makhoul, E. Manolakos, and E. Wilson, editors, Neural Networks for Signal Processing V, pages 475–483. IEEE Service Center, Piscataway, NJ, 1995.Google Scholar
  3. 3.
    C. W. Anderson, E. A. Stolz, and S. Shamsunder. Disciminating mental tasks using EEG represented by AR models. In Proceedings of the 1995 IEEE Engineering in Medicine and Biology Annual Conference. Montreal, Canada, 1995.Google Scholar
  4. 4.
    C. W. Anderson, E. A. Stolz, and S. Shamsunder. Multivariate autoregressive models for classification of spontaneous electroencephalogram during mental tasks. IEEE Transactions on Biomedical Engineering, 45(3):277–286, 1998.CrossRefGoogle Scholar
  5. 5.
    Charles W. Anderson. Effects of variations in neural network topology and output averaging on the discrimination of mental tasks from spontaneous electroencephalogram. Journal of Intelligent Systems, 7(1–2):165–190, 1997.Google Scholar
  6. 6.
    A. S. Gevins and A. Rémond. Methods of Analysis of Brain Electrical and Magnetic Signals, volume 1 of Handbook of Electroencephalography and Clinical Neurophysiology (revised series). Elsevier Science Publishers B.V., New York, NY, 1987.Google Scholar
  7. 7.
    S. Goto, M. Nakamura, and K. Uosaki. On-line spectral estimation of nonstationary time series based on AR model parameter estimation and order selection with a forgetting factor. IEEE Transactions on Signal Processing, 43(6):1519–1522, June 1995.CrossRefGoogle Scholar
  8. 8.
    T. Inouye, K. Shinosaki, A. Iyama, and Y. Matsumoto. Localization of activated areas and directional EEG patterns during mental arithmetic. Electroencephalography and Clinical Neurophysiology, 86(4):224–230, 1993.CrossRefGoogle Scholar
  9. 9.
    H. Jasper. The ten twenty electrode system of the international federation. Electroencephalography and Clinical Neurophysiology, 10:371–375, 1958.Google Scholar
  10. 10.
    I. T. Jollife. Principal Component Analysis. Springer-Verlag, New York, 1986.Google Scholar
  11. 11.
    S. M. Kay. Modern Spectral Estimation: Theory and Application. Prentice-Hall, Englewood Cliffs, NJ, 1988.MATHGoogle Scholar
  12. 12.
    Z. A. Keirn and J. I. Aunon. A new mode of communication between man and his surroundings. IEEE Transactions on Biomedical Engineering, 37(12):1209–1214, December 1990.CrossRefGoogle Scholar
  13. 13.
    Shiao-Lin Lin, Yi-Jean Tsai, and Cheng-Yuan Liou. Conscious mental tasks and their EEG signals. Medical & Biological Engineering & Computing, 31:421–425, 1993.CrossRefGoogle Scholar
  14. 14.
    H. S. Lusted and R. B. Knapp. Controlling computers with neural signals. Scientific American, pages 82–87, October 1996.Google Scholar
  15. 15.
    Scott Makeig, Tzyy-Ping Junj, and Terrence J. Sejnowski. Using feedforward neural networks to monitor alertness from changes in EEG correlation and coherence. In D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 931–937, The MIT Press, Cambridge, MA, 1996.Google Scholar
  16. 16.
    M. Osaka. Peak alpha frequency of EEG during a mental task: Task difficulty and hemispheric differences. Psychophysiology, 21:101–105, 1984.Google Scholar
  17. 17.
    D. E. Rumelhart, G. E. Hinton, and R. W. Williams. Learning internal representations by error propagation. In D. E. Rumelhart, J. L. McClelland, and The PDP Research Group, editors, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, volume 1. Bradford, Cambridge, MA, 1986.Google Scholar
  18. 18.
    A. C. Sanderson, J. Segen, and E. Richey. Hierarchical modeling of EEG signals. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-2(5):405–414, September 1980.Google Scholar
  19. 19.
    E. Stolz. Multivariate autoregressive models for classification of spontaneous electroencephalogram during mental tasks. Master's thesis, Electrical Engineering Department, Colorado State University, Fort Collins, CO, 1995.Google Scholar
  20. 20.
    S-Y. Tseng, R-C. Chen, F-C. Chong, and T-S. Kuo. Evaluation of parametric methods in EEG signal analysis. Med. Eng. Phys., 17:71–78, January 1995.CrossRefGoogle Scholar
  21. 21.
    A. C. Tsoi, D. S. C. So, and A. Sergejew. Classification of electroencephalogram using artificial neural networks. In J. D. Cowan, G. Tesauro, and J. Alspector, editors, Advances in Neural Information Processing Systems 6, pages 1151–1158. Morgan Kaufmann, San Francisco, CA, 1994.Google Scholar
  22. 22.
    T. P. Yunck and F. B. Tuteur. Comparison of decision rules for automatic EEG classification. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-2(5):420–428, September 1980.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Charles W. Anderson
    • 1
  1. 1.Department of Computer ScienceColorado State UniversityFort CollinsUSA

Personalised recommendations