Buscar en
Revista Iberoamericana de Automática e Informática Industrial RIAI
Toda la web
Inicio Revista Iberoamericana de Automática e Informática Industrial RIAI Selección de Canales en Sistemas BCI basados en Potenciales P300 mediante Intel...
Información de la revista
Vol. 14. Núm. 4.
Páginas 372-383 (Octubre - Diciembre 2017)
Compartir
Compartir
Descargar PDF
Más opciones de artículo
Visitas
3361
Vol. 14. Núm. 4.
Páginas 372-383 (Octubre - Diciembre 2017)
Open Access
Selección de Canales en Sistemas BCI basados en Potenciales P300 mediante Inteligencia de Enjambre
P300-Based Brain-Computer Interface Channel Selection using Swarm Intelligence
Visitas
3361
V. Martínez-Cagigala,
Autor para correspondencia
victor.martinez@gib.tel.uva.es

Autor para correspondencia.
, R. Horneroa,b,c
a Grupo de Ingeniería Biomédica, E.T.S.I. de Telecomunicación, Universidad de Valladolid, Valladolid, España
b IMUVA, Instituto de Investigación en Matemáticas, Universidad de Valladolid, Valladolid, España
c INCYL, Instituto de Neurociencias de Castilla y León, Salamanca, España
Este artículo ha recibido

Under a Creative Commons license
Información del artículo
Resumen
Texto completo
Bibliografía
Descargar PDF
Estadísticas
Resumen

Los sistemas Brain-Computer Interface (BCI) se definen como sistemas de comunicación que monitorizan la actividad cerebral y traducen determinadas características, correspondientes a las intenciones del usuario, en comandos de control de un dispositivo. La selección de canales en los sistemas BCI es fundamental para evitar el sobre-entrenamiento del clasificador, reducir la carga computacional y aumentar la comodidad del usuario. A pesar de que se han desarrollado varios algoritmos con anterioridad para tal fin, las metaheurísticas basadas en inteligencia de enjambre aún no han sido suficientemente explotadas en los sistemas BCI basados en potenciales P300. En este estudio se muestra una comparativa entre cinco métodos de enjambre, basados en el comportamiento de sistemas biológicos, aplicados con el objetivo de optimizar la selección de canales en este tipo de sistemas. Los métodos se han evaluado sobre la base de datos de la “III BCI Competition 2005”, reportando precisiones similares o, en algunos casos, incluso más altas que las obtenidas sin realizar ningún tipo de selección. Dado que los cinco métodos se han demostrado capaces de disminuir drásticamente los 64 canales originales a menos de la mitad sin comprometer el rendimiento del sistema, así como de superar el conjunto típico de 8 canales y el método backward elimination, se concluye que todos ellos son adecuados para su aplicación en la selección de canales en sistemas P300-BCI.

Palabras clave:
Interfaces
aprendizaje automático
sistemas biomédicos
optimización y métodos computacionales
electroencefalografía
sistemas de comunicación
Abstract

Brain-Computer Interfaces (BCI) are direct communication pathways between the brain and the environment that translate certain features, which correspond to users’ intentions, into device control commands. Channel selection in BCI systems is essential to avoid over-fitting, to reduce the computational cost and to increase the users’ comfort. Although several algorithms have previously developed for that purpose, metaheuristics based on swarm intelligence have not been exploited yet in P300-based BCI systems. In this study, a comparative among five different swarm methods, based on the behavior of biological systems, is shown. Those methods have been applied in order to optimize the channel selection procedure in this kind of systems, and have been tested with the ‘III BCI Competition 2005’ database II. Results show that the five methods can achieve similar or even higher accuracies than that obtained without performing any channel selection procedure. Owing to the fact that all the applied methods are able to drastically reduce the required number of channels without compromising the system performance, as well as to overcome the common 8-channel set and the backward elimination algorithm, we conclude that all of them are suitable for use in the P300-BCI systems channel selection procedure.

Keywords:
Interfaces
machine learning
biomedical systems
optimization and computational methods
electroencephalography
communication systems
Referencias
[Bhattacharjee y Sarmah, 2015]
K.K. Bhattacharjee, S.P. Sarmah.
A binary firefly algorithm for knapsack problems, pp. 73-77 http://dx.doi.org/10.1109/IEEM.2015.7385611
[Blankertz et al., 2006]
B. Blankertz, K.-R. Müller, D.J. Krusienski, G. Schalk, J.R. Wolpaw, A. Schlögl, G. Pfurtscheller, J.D.R. Millán, M. Schröder, N. Birbaumer.
The BCI competition III: Validating alternative approaches to actual BCI problems.
IEEE Trans. Neural Syst. Rehabil. Eng., 14 (2006), pp. 153-159
[Bonabeau et al., 1999]
E. Bonabeau, M. Dorigo, G. Theraulaz.
Swarm intelligence: from natural to artificial systems.
Oxford University Press, (1999), http://dx.doi.org/10.1007/s13398-014-0173-7.2
[Brownlee, 2011]
Brownlee, J., 2011. Clever Algorithms: Nature-Inspired Programming Recipes, 2nd Edition. DOI: 10.1017/CBO9781107415324.004.
[Cecotti et al., 2011]
H. Cecotti, B. Rivet, M. Congedo, C. Jutten, O. Bertrand, E. Maby, J. Mattout.
A robust sensor-selection method for P300 brain-computer interfaces.
J. Neural Eng., 8 (2011), pp. 016001
[Clerc y Kennedy, 2002]
M. Clerc, J. Kennedy.
The Particle Swarm–Explosion, Stability, and Convergence in a Multidimensional Complex Space.
IEEE Trans. Evol. Comput., 6 (2002), pp. 58-73
[Colwell et al., 2014]
K.A. Colwell, D.B. Ryan, C.S. Throckmorton, E.W. Sellers, L.M. Collins.
Channel selection methods for the P300 Speller.
J. Neurosci. Methods, 232 (2014), pp. 6-15
[Dorigo y Di Caro, 1999]
M. Dorigo, G. Di Caro.
The Ant Colony Optimization Meta-Heuristic.
New Ideas Optim., 2 (1999), pp. 11-32
[Dorigo y Stützle, 2004]
M. Dorigo, T. Stützle.
Ant Colony Optimization.
The MIT press, (2004),
[Farwell y Donchin, 1988]
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 (1988), pp. 510-523
[Gonzalez et al., 2013]
A. Gonzalez, I. Nambu, H. Hokari, M. Iwahashi, Y. Wada.
Towards the classification of single-trial event-related potentials using adapted wavelets and particle swarm optimization, pp. 3089-3094 http://dx.doi.org/10.1109/SMC.2013.527
[Guyon y Elisseeff, 2003]
I. Guyon, A. Elisseeff.
An Introduction to Variable and Feature Selection.
J. Mach. Learn. Res., 3 (2003), pp. 1157-1182
[Jin et al., 2010]
J. Jin, B.Z. Allison, C. Brunner, B. Wang, X. Wang, J. Zhang, C. Neuper, G. Pfurtscheller.
P300 Chinese input system based on Bayesian LDA.
Biomed. Tech., 55 (2010), pp. 5-18
[Jobson, 1991]
J.D. Jobson.
4th Edition, Springer, (1991),
[Karaboga, 2005]
D. Karaboga.
An Idea Based on Honey Bee Swarm for Numerical Optimization.
Tech. rep., Erciyes University, (2005),
[Karaboga et al., 2014]
D. Karaboga, B. Gorkemli, C. Ozturk, N. Karaboga.
A comprehensive survey: Artificial bee colony (ABC) algorithm and applications.
Artif. Intell. Rev., 42 (2014), pp. 21-57
[Kee et al., 2015]
C.-Y. Kee, S. Ponnambalam, C.-K. Loo.
Multi-objective genetic algorithm as channel selection method for P300 and motor imagery data set.
Neurocomputing, 161 (2015), pp. 120-131
[Kennedy y Eberhart, 1995]
Kennedy, J., Eberhart, R., 1995. Particle swarm optimization. Neural Networks, 1995. Proceedings., IEEE Int. Conf. 4, 1942-1948 vol.4. DOI: 10.1109/ICNN.1995.488968.
[Kennedy y Eberhart, 1997]
Kennedy, J., Eberhart, R., 1997. A Discrete Binary Version of the Particle Swarm Algorithm. 1997 IEEE Int. Conf. Syst. Man, Cybern. Comput. Cybern. Simul. 5, 4-8. DOI: 10.1109/ICSMC.1997.637339.
[Kennedy et al., 2001]
J. Kennedy, R.C. Eberhart, Y. Shi.
[Kiran, 2015]
M.S. Kiran.
The continuous artificial bee colony algorithm for binary optimization.
Appl. Soft Comput. J., 33 (2015), pp. 15-23
[Konak et al., 2006]
A. Konak, D.W. Coit, A.E. Smith.
Multi-objective optimization using genetic algorithms: A tutorial.
Reliab. Eng. Syst. Saf., 91 (2006), pp. 992-1007
[Kong et al., 2008]
M. Kong, P. Tian, Y. Kao.
A new ant colony optimization algorithm for the multidimensional Knapsack problem.
Comput. Oper. Res., 35 (2008), pp. 2672-2683
[Krüger et al., 2016]
T.J. Krüger, T. Davidović, D. Teodorović, M. Šelmić.
The bee colony optimization algorithm and its convergence.
Int. J. Bio-Inspired Comput., 8 (2016), pp. 340-354
[Krusienski et al., 2008]
D. Krusienski, E. Sellers, D. McFarland, T. Vaughan, J. Wolpaw.
Toward enhanced P300 speller performance.
J. Neurosci. Methods, 167 (2008), pp. 15-21
[Kübler y Birbaumer, 2008]
A. Kübler, N. Birbaumer.
Brain-computer interfaces and communication in paralysis: Extinction of goal directed thinking in completely paralysed patients?.
Clin. Neurophysiol., 119 (2008), pp. 2658-2666
[Kübler et al., 2007]
A. Kübler, F. Nijboer, N. Birbaumer.
Brain-Computer Interfaces for communication and motor control – perspectives on clinical application. En: Toward Brain-Computer Interfacing.
1st Edition, The MIT Press, (2007), pp. 373-391
[Martínez-Cagigal et al., 2016]
Martínez-Cagigal, V., Gomez-Pilar, J., Álvarez, D., Hornero, R., 2016. An asynchronous P300-based brain-computer interface web browser for severely disabled people. IEEE Transactions on Neural Systems and Rehabilitation Engineering (Aceptado). DOI: 10.1109/TNSRE.2016.2623381.
[Perseh y Sharafat, 2012]
B. Perseh, A.R. Sharafat.
An Efficient P300-based BCI Using Wavelet Features and IBPSO-based Channel Selection.
J. Med. Signals Sens., 2 (jun 2012), pp. 128-143
[Pham et al., 2006]
D.T. Pham, A. Ghanbarzadeh, E. Koç, S. Otri, S. Rahim, M. Zaidi.
The Bees Algorithm - A Novel Tool for Complex Optimisation Problems, pp. 454-459 http://dx.doi.org/10.1016/B978-008045157-2/50081-X
[Rakotomamonjy y Guigue, 2008]
A. Rakotomamonjy, V. Guigue.
BCI Competition III: Dataset II - Ensemble of SVMs for BCI P300 Speller.
IEEE Trans. Biomed. Eng., 55 (2008), pp. 1147-1154
[Rivet et al., 2012]
B. Rivet, H. Cecotti, E. Maby, J. Mattout.
Impact of spatial filters during sensor selection in a visual P300 brain-computer interface.
Brain Topogr., 25 (2012), pp. 55-63
[Rivet et al., 2010]
B. Rivet, H. Cecotti, R. Phlypo, O. Bertrand, E. Maby, J. Mattout.
EEG sensor selection by sparse spatial filtering in P300 speller Brain-Computer Interface, pp. 5379-5382 http://dx.doi.org/10.1109/IEMBS.2010.5626485
[Salvaris y Sepulveda, 2009]
M. Salvaris, F. Sepulveda.
Visual modifications on the p300 speller bci paradigm.
Journal of neural engineering, 6 (2009), pp. 046011
[Schalk et al., 2004]
G. Schalk, D.J. McFarland, T. Hinterberger, N. Birbaumer, J.R. Wolpaw.
BCI2000: A general-purpose brain-computer interface (BCI) system.
IEEE Trans. Biomed. Eng., 51 (2004), pp. 1034-1043
[Witten y Frank, 2011]
I.H. Witten, E. Frank.
Data Mining: Practical Machine Learning Tools and Techniques.
3rd Edition, Morgan Kaufmann, (2011),
[Wolpaw et al., 2000]
J.R. Wolpaw, N. Birbaumer, W.J. Heetderks, D.J. McFarland, P.H. Peckham, G. Schalk, E. Donchin, L.A. Quatrano, C.J. Robinson, T.M. Vaughan.
Brain-computer interface technology: a review of the first international meeting.
IEEE Trans. Rehabil. Eng., 8 (2000), pp. 164-173
[Wolpaw et al., 2002]
J.R. Wolpaw, N. Birbaumer, D.J. McFarland, G. Pfurtscheller, T.M. Vaughan.
Brain-computer interfaces for communication and control.
Clin. Neurophysiol., 113 (2002), pp. 767-791
[Xu et al., 2013]
M. Xu, H. Qi, L. Ma, C. Sun, L. Zhang, B. Wan, T. Yin, D. Ming.
Channel Selection Based on Phase Measurement in P300-Based Brain-Computer Interface.
[Yang, 2009]
Yang, X. S., 2009. Firefly Algorithms for Multimodal Optimization. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 5792 LNCS, 169-178. DOI: 10.1007/978-3-642-04944-6_14.
[Yang, 2014]
X.-S. Yang.
Nature-Inspired Optimization Algorithms.
1st Edition, Elsevier Inc, (2014),
[Yang et al., 2013]
X.-S. Yang, Z. Cui, R. Xiao, A.H. Gandomi, M. Karamanoglu.
Swarm Intelligence and Bio-Inspired Computation: Theory and Applications.
1st Edition, Elsevier Inc, (2013), http://dx.doi.org/10.1016/B978-0-12-405163-8.00020-X
[Yu et al., 2015]
T. Yu, Z. Yu, Z. Gu, Y. Li.
Grouped Automatic Relevance Determination and Its Application in Channel Selection for P300 BCIs.
IEEE Trans. Neural Syst. Rehabil. Eng., 23 (2015), pp. 1068-1077
Opciones de artículo
Herramientas