Human Brain Interface: Signal Processing and Machine Learning
Jean-Marc Vesin,
Ulrich Hoffmann,
Touradj Ebrahimi,
Jean-Marc Vesin
Signal Processing Institute EPFL, Lausanne, Switzerland
Search for more papers by this authorUlrich Hoffmann
Signal Processing Institute EPFL, Lausanne, Switzerland
Search for more papers by this authorTouradj Ebrahimi
Signal Processing Institute EPFL, Lausanne, Switzerland
Search for more papers by this authorJean-Marc Vesin,
Ulrich Hoffmann,
Touradj Ebrahimi,
Jean-Marc Vesin
Signal Processing Institute EPFL, Lausanne, Switzerland
Search for more papers by this authorUlrich Hoffmann
Signal Processing Institute EPFL, Lausanne, Switzerland
Search for more papers by this authorTouradj Ebrahimi
Signal Processing Institute EPFL, Lausanne, Switzerland
Search for more papers by this authorFirst published: 14 April 2006
Abstract
The Electroencephalogram (EEG) is a recording of the electrical potentials generated by brain activity on the scalp. It has been used for decades as a non-invasive tool both in fundamental brain research and in clinical diagnosis. But it is now widely used also in Brain-Computer Interfaces (BCI) to provide augmentative communication mainly for severely handicapped patients and, prospectively, in the general frame work of human computer interaction. As in any communication system, the input (EEG activity) must be coded (feature extraction) before being sent, and the receiving device (the computer) must map the received data to actions (classication). This article explores the main approaches used in the BCI community for completing these tasks.
Bibliography
- 1J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, and T. M. Vaughan, Brain-computer interfaces for communication and control. Clinical Neurophysiology 2002; 113(6): 767–791.
- 2T. Ebrahimi, J.-M. Vesin, and G. N. Garcia, Brain-computer interface in multimedia communication. IEEE Signal Processing Magazine 2003; 20(1): 14–24.
- 3G. Pfurtscheller and C. Neuper, Motor imagery and direct brain-computer communication. Proceedings of the IEEE 2001; 89(7): 1123–1134.
- 4P. Durka, J. Zygierewicz, H. Klekowicz, J. Ginter, and K. Blinowska, On the statistical signicance of event-related EEG desynchronization and synchronization in the time-frequency plane. IEEE Transactions on Biomedical Engineering 2004; 51(7): 1167–1175.
- 5E. L. Glassman, A wavelet-like filter based on neuron action potentials for analysis of human scalp electroencephalographs. IEEE Transactions on Biomedical Engineering 2005; 52: 1852–1862.
- 6G. Pfurtscheller, C. Neuper, A. Schlögl, and K. Lugger, Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Transactions on Rehabilitation Engineering 1998; 6: 316–325.
- 7D. Burke, S. Kelly, P. De Chazal, R. Reilly, and C. Finucane, A parametric feature extraction and classication strategy for brain-computer interfacing. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2005; 13(1): 12–17.
- 8C. Anderson, E. Stolz, and S. Shamsunder, Multivariate autoregressive models for classication of spontaneous electroencephalographic signals during mental tasks. IEEE Transactions on Biomedical Engineering 1998; 45(3): 277–286.
- 9E. Gysels and P. Celka, Phase synchronization for the recognition of mental tasks in a brain-computer interface. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2004; 12(4): 406–415.
- 10M. H. Hayes, Statistical Digital Signal Processing and Modeling. Wiley, 1996.
- 11S. Blanco, H. Garcia, R. Quiroga, L. Romanelli, and O. Rosso, Stationarity of the EEG series. IEEE Engineering in Medicine and Biology Magazine 1995; 14(4): 395–399.
- 12M. Amin, A new approach to recursive fourier transform. Proceedings of the IEEE 1987; 75(11): 1537–1538.
- 13L. Cohen, Time-Frequency Analysis. Englewood Cliffs, NJ: Prentice Hall, 1996.
- 14S. Haykin, R. Racine, Y. Xu, and C. Chapman, Monitoring neuronal oscillations and signal transmission between cortical regions using time-frequency analysis of electroencephalographic activity. Proceedings of the IEEE 1996; 84(9); 1295–1301.
- 15P. S. Addison, The Illustrated Wavelet Trans form Handbook. Bristol: IOP, 2002.
10.1887/0750306920 Google Scholar
- 16P. Durka and K. Blinowska, A unified time-frequency parametrization of EEGs. IEEE Engineering in Medicine and Biology Magzine 2001; 20: 47–53.
- 17P. D. Grünwald, I. J. Myung, and P. M. A., Advances in Minimum Description Length Theory and Applications Cambridge, MA: MIT Press, 2005.
10.7551/mitpress/1114.001.0001 Google Scholar
- 18E. Bagarinao and S. Sato, Algorithm for vector autoregressive model parameter estimation using an orthogonalization procedure. Annals of Biomedical Engineering 2002; 30(2): 260–271.
- 19M. Cassidy and W. Penny, Bayesian nonstationary autoregressive models for biomedical signal analysis. IEEE Transactions on Biomedical Engineering 2002; 49(10): 1142–1152.
- 20P. Sykacek, S. Roberts, and M. Stokes, Adaptive BCI based on variational bayesian kalman filtering: An empirical evaluation. IEEE Transactions on Biomedical Engineering 2004; 51(5): 719–727.
- 21A. Pikovsky, M. Rosenblum, and J. Kurths, Synchronization–A Universal Conceptin Nonlinear Sciences. Cambridge, UK: Cambridge University Press, 2001.
10.1017/CBO9780511755743 Google Scholar
- 22J. R. Wolpaw, D. J. McFarland, G. W. Neat, and C. A. Forneris, An EEG-based brain-computer interface for cursor control. Electroencephalography and Clinical Neurophysiology 1991; 78: 252–259.
- 23V. Vapnik, The Nature of Statistical Learning Theory New York: Springer, 1999.
- 24M. Kaper, P. Meinicke, U. Grosskathoefer, T. Lingner, and H. Ritter, Support vector machines for the P300 speller paradigm. IEEE Transactions on Biomedical Engineering 2004; 51(6): 1073–1076.
- 25B. Obermaier, C. Neuper, C. Guger, and G. Pfurtscheller, Information transfer rate in a five-classes brain-computer interface. IEEE Transactions on Neural Systems and Rehabilitati on Engineering 2001; 9(3): 283–288.
- 26K. R. Müller, C. W. Anderson, and G. E. Birch, Linear and nonlinear methods for brain-computer interfaces. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2003; 11: 165–169.
- 27B. Blankertz, G. Curio, and K. R. Müller, Classifying single trial EEG: Towards brain computer interfacing. in Advances in Neural Information Processing Systems, vol. 14. MIT Press, 2002.
- 28T. Lal, M. Schröder, T. Hinterberger, J. Weston, M. Bogdan, N. Birbaumer, and B. Schölkopf, Support vector channel selection in BCI. IEEE Transactions on Biomedical Engineering 2004; 51(6): 1003–1010.
- 29E. Yom-Tov and G. Inbar, Feature selection for the classication of movements from single movement-related potentials. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2002; 10(3): 170–177.
- 30K. Müller, S. Mika, G. Rätsch, K. Tsuda, and B. Schölkopf, An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks 2001; 12(2): 181–201.
- 31G. N. Garcia, Direct brain-computer communication through scalp recorded EEG signals. Ph.D. dissertation, École Polytechnique Fédérale de Lausanne, 2004.
