Abstract
We propose the use of genetic programming (GP) as a means to evolve brain–computer interfaces for mouse control. Our objective is to synthesise complete systems, which analyse electrical brain signals and directly transform them into pointer movements, almost from scratch, the only input provided by us in the process being the set of visual stimuli to be used to generate recognisable brain activity. Experimental results with our GP approach are very promising and compare favourably with those produced by support vector machines.
Similar content being viewed by others
Notes
Some of this work has appeared in a much shorter paper published in proceedings of EuroGP 2011 [24].
While focusing attention on the target stimulus is a requirement, the amplitude of the P300 is significantly enhanced if, additionally, a task is assigned to the occurrence of such a stimulus [25] as long as task demands are still within a subject’s capabilities. In previous experiments we found that naming target colours produced the strongest P300s.
As in [17] the SVM classifier was implemented as an ensemble of 6 linear SVMs, with each SVM trained on a subset of the collected data across all the channels. All channels were used to train the SVMs since it has been shown that channel selection, when used in conjunction with SVMs, only marginally improves results [26].
References
L.A. Farwell, E. Donchin, Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr. Clin. Neurophysiol. 70, 510–523 (1988)
J.R. Wolpaw, D.J. McFarland, G.W. Neat, C.A. Forneris, An EEG-based brain–computer interface for cursor control. Electroencephalogr. Clin. Neurophysiol. 78, 252–259 (1991)
G. Pfurtscheller, D. Flotzinger, J. Kalcher, Brain–computer interface: a new communication device for handicapped persons. J. Microcomput. Appl. 16(3), 293–299 (1993)
N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversen, B. Kotchoubey, A. Kbler, J. Perelmouter, E. Taub, H. Flor, A spelling device for the paralysed. Nature 398, 297–298 (1999)
J.R. Wolpaw, D.J. McFarland, Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. Proc. Natl. Acad. Sci. 101(51), 17849–17854 (2004)
J.B. Polikoff, H.T. Bunnell, W J. Borkowski Jr., Toward a P300-based computer interface, in Rehabilitation Engineering and Assistive Technology Society of North America (RESNA’95) (Arlington, Va) (Resna Press, 1995), pp. 178–180
F. Beverina, G. Palmas, S. Silvoni, F. Piccione, S. Giove, User adaptive BCIs: SSVEP and P300 based interfaces. PsychNol. J. 1(4), 331–354 (2003)
L. Citi, R. Poli, C. Cinel, F. Sepulveda, P300-based BCI mouse with genetically-optimized analogue control. IEEE Trans. Neural Syst. Rehabil. Eng. 16, 51–61 (2008)
M. Salvaris, C. Cinel, R. Poli, Novel sequential protocols for a ERP based BCI mouse. 5th international IEEE EMBS neural engineering conference, IEEE Press, 2011, pp. 352–355
J.R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection. (MIT Press, Cambridge, MA, USA, 1992)
R. Poli, W. B. Langdon, N. F. McPhee, A field guide to genetic programming (2008), Published via http://lulu.com and freely available at http://www.gp-field-guide.org.uk (With contributions by J. R. Koza)
J. Donoghue, Connecting cortex to machines: recent advances in brain interfaces. Nat. Neurosci. 5, 1085–1088 (2002)
P. Comon, Independent component analysis, a new concept? Signal Process. 36, 287–314 (1994)
S. Makeig, A.J. Bell, T.-P. Jung, T.J. Sejnowski, Independent component analysis of electroencephalographic data, in Advances in Neural Information Processing Systems, vol. 8, ed. by D S. Touretzky, M.C. Mozer, M.E. Hasselmo (The MIT Press, Cambridge, MA, 1996), pp. 145–151
C. Cortes, V. Vapnik, Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
R. Poli, L. Citi, F. Sepulveda, C. Cinel, Analogue evolutionary brain computer interfaces. IEEE Comput. Intell. Mag. 4, 27–31 (2009)
M. Salvaris, C. Cinel, R. Poli, L. Citi, F. Sepulveda, Exploring multiple protocols for a brain–computer interface mouse, in Proceedings of 32nd IEEE EMBS Conference, Buenos Aires, pp. 4189–4192, Sept 2010
J. Wolpaw, N. Birbaumer, W. Heetderks, D. McFarland, P. Peckham, G. Schalk, E. Donchin, L. Quatrano, C. Robinson, T. Vaughan, Brain–computer interface technology: a review of the first international meeting. Rehabil. Eng. IEEE Trans. 8(2), 164–173 (2000)
D.J. Montana, Strongly typed genetic programming. Evol. Comput. 3(2), 199–230 (1995)
L. Citi, R. Poli, C. Cinel, Documenting, modelling and exploiting P300 amplitude changes due to variable target delays in Donchin’s speller. J. Neural Eng. 7(5), 056006 (2010)
J. R. Koza, Human-competitive results produced by genetic programming. Genet. Programm. Evolvable Mach. 11, 251–284, Sept 2010. Tenth Anniversary Issue: Progress in Genetic Programming and Evolvable Machines
R. Poli, M. Salvaris, C. Cinel, Evolutionary synthesis of a trajectory integrator for an analogue brain–computer interface mouse, in Applications of Evolutionary Computation (EvoApplications), vol. 6624 of Lecture Notes in Computer Science, ed. by C.D. Chio, S. Cagnoni, C. Cotta, M. Ebner, A. Ekárt, A. Esparcia-Alcázar, J.J.M. Guervós, F. Neri, M. Preuss, H. Richter, J. Togelius, G.N. Yannakakis (Springer, Berlin, 2011), pp. 214–223
R. Poli, M. Salvaris, C. Cinel, Evolution of an effective brain-computer interface mouse via genetic programming with adaptive Tarpeian bloat control, in Genetic Programming Theory and Practice IX, ed. by R. Riolo, E. Vladislavleva, J.H. Moore (Springer, New York, 2011), forthcoming
R. Poli, M. Salvaris, C. Cinel, Evolution of a brain–computer interface mouse via genetic programming, in Proceedings of Genetic Programming—14th European Conference, EuroGP, no. 6621 in Lecture Notes in Computer Science, ed. by S. Silva, J.A. Foster, M. Nicolau, P. Machado, M. Giacobini (Springer, Berlin, 2011) pp. 203–214
W.S. Pritchard, Psychophysiology of P300. Psychol. Bull. 89, 506–540 (1981)
A. Rakotomamonjy, V. Guigue, BCI competition III: dataset II—ensemble of SVMs for BCI P300 speller. IEEE Trans. Biomed. Eng. 55, 1147–1154 (2008)
Acknowledgments
We would like to thank EPSRC (grant EP/F033818/1) for financial support. We would also like to thank the reviewers for their very useful comments.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Poli, R., Salvaris, M. & Cinel, C. A genetic programming approach to the evolution of brain–computer interfaces for 2-D mouse–pointer control. Genet Program Evolvable Mach 13, 377–405 (2012). https://doi.org/10.1007/s10710-012-9161-x
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10710-012-9161-x