FuRIA : un nouvel algorithme d’extraction de caractéristiques pour les interfaces cerveauordinateur utilisant modèles inverses et modèles flous - FuRIA: a new feature extraction algorithm for braincomputer interfaces using fuzzy and inverse models

FuRIA : un nouvel algorithme d’extraction de caractéristiques pour les interfaces cerveauordinateur utilisant modèles inverses et modèles flous

FuRIA: a new feature extraction algorithm for braincomputer interfaces using fuzzy and inverse models

Fabien Lotte Anatole Lécuyer  Bruno Arnaldi 

IRISA-INSA Rennes, 20 avenue des buttes de coesmes, 35043 Rennes Cedex, France

IRISA-INRIA Rennes, avenue du général Leclerc, Campus Universitaire de Beaulieu, 35042 Rennes Cedex, France

Corresponding Author Email: 
fabien.lotte.irisa.fr
Page: 
305-317
|
Received: 
15 April 2008
|
Accepted: 
N/A
|
Published: 
31 August 2008
| Citation

OPEN ACCESS

Abstract: 

When using Brain-Computer Interfaces (BCI) based on ElectroEncephaloGraphy (EEG), the identification of mental tasks relies on two main points: feature extraction and classification [MAM+06, BFWB07, LCL+07]. Feature extraction aims at describing EEG signals by a few relevant values called “features”, whereas classification aims at automatically assigning a class to these features. In this paper we focus on feature extraction, as the BCI community has stressed the need to explore new feature extraction algorithms [MAM+06].

Recently, inverse models have been revealed as promising feature extraction algorithms for BCI [QDH04, GGP+05, WGWB05, CLL06]. Such models aims at computing the activity in the whole brain volume, by using only scalp EEG signals and a head model representing the brain as a set of voxels (volume elements). The activity computed in a few brain regions has been used as features for BCI systems.

Despite good results, some limitations remain. Indeed, it seems that current methods cannot conciliate genericity, i.e., the capability to deal with any kind of mental task, and the fact of generating few features. On one hand, methods that are generic and automatic tend to generate a large number of features, as they extract several features for each voxel [GGP+05]. The activity in neighboring voxels can be correlated and, as such, it would be more appropriate to gather these voxels in brain regions. On the other hand, methods that generate few features have been proposed, but they are not generic anymore as they need a priori knowledge on the mental tasks used, and are currently limited to motor imagerybased BCI [QDH04, WGWB05]. Recently, we have proposed a method which is generic and which generates few features, as voxels whose activity is correlated are gathered into Regions Of Interest (ROI) [CLL06]. However, this method is not completely automatic and is limited to the use of two ROI whose spatial extension is hard to define [CLL06].

In this paper, we propose a generic feature extraction algorithm which can automatically identify any number of relevant ROI and can properly define their spatial extension thanks to the new concept of fuzzy ROI. This algorithm is known as FuRIA, which stands for “Fuzzy Region of Interest Activity”.

Résumé

Cet article propose un nouvel algorithme d’extraction de caractéristiques pour les Interfaces CerveauOrdinateur (ICO) basées sur l’électroencéphalographie. Cet algorithme utilise les modèles inverses ainsi que le nouveau concept de Région d’Intérêt (RI) floue. Il peut automatiquement identifier les RI pertinentes pour la discrimination ainsi que les bandes de fréquences dans lesquelles ces RI sont les plus discriminantes. Les activités calculées dans ces RI peuvent ensuite être utilisées comme caractéristiques d’entrée pour n’importe quel classifieur. Une première évaluation de l’algorithme, utilisant une Machine à Vecteurs Supports (SVM) comme classifieur, est présentée sur le jeu de données IV de la «BCI competition 2003». Les résultats s’avèrent prometteurs avec une précision sur l’ensemble de test allant de 85% à 86% contre 84% pour le gagnant de la compétition sur ces données. Enfin, nous montrons que combiner ce nouvel algorithme avec des systèmes d’inférence flous permet de concevoir des ICO potentiellement interprétables.

Keywords: 

brain-computer interface (BCI), feature extraction, inverse model, source localization, classification, interpretability, fuzzy set, electroencephalography (EEG).

Mots clés

interface cerveau-ordinateur (ICO), extraction de caractéristiques, modèle inverse, localisation de sources, classification, interprétabilité, ensemble flou, électroencéphalographie (EEG).

1. Introduction
2. Interfaces Cerveauordinateur Et Modèles Inverses : Un État-De-L’art
3. L’algorithme FuRIA
4. Implémentation De L’algorithme
5. Évaluation
6. Conclusion Et Travaux Futurs
  References

[BCM+07] F. BABILONI, F. CINCOTTI, M. MARCIANI, S. SALINARI, L. ASTOLFI, A. TOCCI, F. ALOISE, F. DE VICO FALLANI, S. BUFALARI and D. MATTIA, «The Estimation of Cortical Activity for Brain-Computer Interface: Applications in a Domotic Context», Computational Intelligence and Neuroscience, 2007 (2007).

[BFWB07] A. BASHASHATI, M. FATOURECH, R. K. WARD and G. E. BIRCH, «A Survey of Signal Processing Algorithms in BrainComputer Interfaces Based on Electrical Brain Signals», Journal of Neural engineering, 4, (2207), n° 2, R35-57.

[BGM07] M. BESSERVE, L. GARNERO and J. MARTINERIE, «De l'estimation à la classification des activités corticales pour les interfaces cerveau-machine », in Proc. GRETSI, 2007.

[Bir06] N. BIRBAUMER, «Breaking the silence: Brain-computer interfaces (BCI) for communication and motor control », Psychophysiology, 43 (2006), n° 6, p.517-532.

[BKG+00] N. BIRBAUMER, A. KÜBLER, N. GHANAYIM, T. HINTERBERGER, J. PERELMOUTER, J. KAISER, I. IVERSEN, B. KOTCHOUBEY, N. NEUMANN and H. FLOR, «The Thought Translation Device (TTD) for completely paralyzed patients», IEEE Transactions on Rehabilitation Engineering, 8 (2000), p. 190-193.

[BMC+04] B. BLANKERTZ, K. R. MÜLLER, G. CURIO, T. M. VAUGHAN, G. SCHALK, J. R. WOLPAW, A. SCHLÖGL, C. NEUPER, G. PFURTSCHELLER, T. HINTERBERGER and M. SCHRÖDER and N. BIRBAUMER, «The BCI competition 2003: Progress and perspectives in detection and discrimination of EEG single trials», IEEE Transactions on Biomedical Engeneering, 51 (2204), n° 6, p.1044-1051.

[Bur98] C. J. C. BURGES, «A Tutorial on Support Vector Machines for Pattern Recognition », Knowledge Discovery and Data Mining, 2 (1998), p.121-167.

[CLL06] M. CONGEDO, F. LOTTE, A. LÉCUYER, «Classsification of Movement Intention by Spatially Filtered Electromagnetic Inverse Solutions», Physics in Medicine and Biology, 51 (2006), p. 1971-1989.

[CM02] D. COMANICIU, P. MEER, «Mean Shift –– A Robust Approach toward Feature Space Analysis », IEEE Transactions on Pattern Analysis and Machine Intelligence, 24 (2002), n° 5, p. 603-619.

[Con6] M. CONGEDO, «Subspace Projection Filters for Real-Time Brain Electromagnetic Imaging », IEEE Transactions on Biomedical Engineering, 53 (2006), n° 8, p. 1624-1634.

[Cor02] A. CORNUÉJOLS, «Une introduction aux SVM », Bulletin de l'AFIA (Association Française d'Intelligence Artificielle), 51 (2002).

[CR07] F. CABESTAING and A. RAKOTOMAMONJY, «Introduction aux interfaces cerveau-machine (BCI) », in 21ème Colloque sur le Traitement du Signal et des Images, GRETSI`07, 2007, p.617-620.

[dRMFn+02] J. DEL R. MILLÁN, M. FRANZÉ, J. MOURIÑO, F. CINCOTTI and F. BABILONI, «Relevant EEG features for the classification of spontaneous motor-related tasks, Biological Cybernetics, 86 (2002), n° 2, p. 89-95.

[GGP+05] R. GRAVE DE PERALTA MENENDEZ, S. GONZALEZ ANDINO, L. PEREZ, P.W. FERREZ and J. DEL R. MILLÁN, «NonInvasive Estimation of Local Field Potentials for Neuroprosthesis Control», Cognitive Processing, Special Issue on Motor Planning in Humans and Neuroprosthesis Control, 6 (2005), p. 59-64.

[GHHP99] C. GUGE, W. HARKAM, C. HERTNAES and G. PFURTSCHELLER, «Prosthetic control by an EEG-based braincomputer interface (BCI)», Proc. AAATE 5th European Conference for the Advancement of Assistive Technology, 1999.

[HBWF96] A. P. HOLMES, R. C. BLAIR, J. D. WATSON and I. FORD, «Nonparametric analysis of statistic images from functional mapping experiments, Journal of Cerebral Blood Flow and Metabolism, 16 (1996), p. 7-22.

[JAPAMBYS06] J.R. JIMENEZ-ALANIZ, M. POHL-ALFARO, V. MEDINA-BANUELOS and O. YANEZ-SUAREZ, « Segmenting Brain MRI using Adaptive Mean Shift », 28th International IEEE EMBS Annual Conference, 2006, p. 3114-3117.

[KLH05] B. KAMOUSI, Z. LIU and B. HE, «Classification of Motor Imagery Tasks for Brain-Computer Interface Applications by means of Two Equivalent Dipoles Analysis », IEEE Transactions on Neural Systems and Rehabilitation Engineering, 13 (2005), p. 166-171.

[LCL+07] F. LOTTE, M. CONGEDO, A. LÉCUYER, F. LAMARCHE and B. ARNALDI, «A Review of classification algorithms for EEG-based BrainComputer Interfaces», Journal of Neural Engineering, 4 (2007), p.R1-R13.

[LLA07a] F. LOTTE, A. LÉCUYER and B. ARNALDI, «FuRIA : un nouvel algorithme d'extraction de caractéristiques pour les interfaces cerveau-ordinateur utilisant modèles inverses et modèles flous », in Colloque GRETSI, 2007, p. 665-668.

[LLA07b] F. LOTTE, A. LÉCUYER and B. ARNALDI, «Les Interfaces Cerveau-Ordinateur : Utilisation en Robotique et Avancées Récentes», Journées Nationales de la Recherche en Robotique, 2007.

[LLLA07] F. LOTTE, A. LÉCUYER, F. LAMARCHE and B. ARNALDI, «Studying the Use of Fuzzy Inference Systems for Motor Imagery Classification », IEEE Transactions on Neural System and Rehabilitation Engineering, 15 (2007), n° 2, p. 322-324.

[LLR+06] F. LOTTE, A. LÉCUYER, Y. RENARD, F. LAMARCHE and B. ARNALDI, «Classification de Données Cérébrales par Système d'Inférence Flou pour l'Utilisation d'Interfaces Cerveau-Ordinateur en Réalité Virtuelle », in Actes des Premières Journées de l'Association Française de Réalité Virtuelle, AFRV06, 2006, p. 55-62.

[LNM06] R. LEHEMBRE, Q. NOIRHOMME and B. MACQ, «Inverse Problem Applied to BCI's : Keeping Track of the EEG's Brain Dynamics Using Kalman Filtering, in Proc. of the 3rd Internationnal Brain Computer Interface Workshop, 2006, p. 32-33.

[Lot06] F. LOTTE, «The use of Fuzzy Inference Systems for classification in EEG-based Brain-Computer Interfaces», in Proc. of the 3rd international Brain-Computer Interface workshop, 2006, p. 12-13.

[LSF+07] R. LEEB, R. SCHERER, D. FRIEDMAN, F. LEE, C. KEINRATH, H. BISCHOF, M. SLATER and G. PFURTSCHELLER, «Towards brain-computer interfacing», ch. Combining BCI and Virtual Reality: Scouting Virtual Worlds, MIT Press, G. Dornhege, R. Millan Jdel, T. Hinterberger, D. J. McFarland & K. R. Müller éd., 2007.

[MAM+06] D. J. MCFARLAND, C. W. ANDERSON, K.-R. MULLER, A. SCHLOGL and D. J. KRUSIENSKI, «BCI meeting 2005-workshop on BCI signal processing: feature extraction and translation », IEEE Transactions on Neural Systems and Rehabilitation Engineering, 14 (2006), n° 2, p. 135-138.

[MBF+07] S.G. MASON, A. BASHASHATI, M. FATOURECHI, K.F. NAVARRO and G.E. BIRCH, «A Comprehensive Survey of Brain Interface Technology Designs », Annals of Biomedical Engineering, 35 (2007), n° 2, p. 137-169.

[MML+04] C.M. MICHEL, M.M. MURRAY, G. LANTZ, S. GONZALEZ, L. SPINELLI and R. GRAVE DE PERALTA, « EEG source imaging», Clin Neurophysiol, 115 (2004), n° 10, p. 2195-2222.

[MPP08] G.R. MULLER-PUTZ and G. PFURTSCHELLER, «Control of an Electrical Prosthesis With an SSVEP-Based BCI », IEEE Transactions on Biomedical Engineering, 55 (2008), n° 1, p.361-364.

[MRMG04] J. R. MILLÁN, F. RENKENS, J. MOURINO and W. GERSTNER, «Noninvasive brain-actuated control of a mobile robot by human EEG », IEEE Transactions on Biomedical Engineering, 51 (2004), n°6, p. 1026-1033.

[NdS05] E. NIEDERMEYER and F. LOPES DA SILVA, Electroencephalography: basic principles, clinical applications, and related fields, 5th éd., Lippincott Williams & Wilkins, ISBN 0781751268, 2005.

[NKM08] Q. NOIRHOMME, R.I. KITNEY and B. MACQ, «Single Trial EEG Source Reconstruction for Brain-Computer Interface, IEEE Transactions on Biomedical Engineering, 55 (2008), n° 5, p. 1592-1601.

[Pfu99] G. PFURTSCHELLER, «EEG event-related desynchronization (ERD) and event-related synchronization (ERS) », Electroencephalography: Basic Principles, Clinical Applications and Related Fields, 4th ed. (1999), p. 958,967.

[PGN06] G. PFURTSCHELLER, B. GRAIMANN and C. NEUPER, «Wiley Encyclopedia of Biomedical Engineering », ch. EEG-Based Brain-Computer Interface System, John Wiley & Sons, Inc., 2006.

[PM] R.D. PASCUAL-MARQUI, «LORETA/sLORETA website».

[PM99] R.D. PASCUAL-MARQUI, «Review of methods for solving the EEG inverse problem », International Journal of Bioelectromagnetism, 1 (1999), p. 75-86.

[PM02] R.D. PASCUAL-MARQUI, « Standardized low resolution brain electromagnetic tomography ({sLORETA}) : technical details », Methods and Findings in Experimental and Clinical Pharmacology, 24D (2002), p. 5-12.

[PM07] R.D. PASCUAL-MARQUI, «Discrete, 3D distributed, linear imaging methods of electric neuronal activity. Part 1: exact, zero error localization », Tech. report, arXiv:0710.3341v2, 2007.

[QDH04] L. QIN, L. DING and B. HE, «Motor Imagery Classification by Means of Source Analysis for Brain Computer Interface Applications», Journal of Neural Engineering, 1 (2004), n° 3, p. 135-141.

[RBG+07] B. REBSAMEN, E. BURDET, C. GUAN, H. ZHANG, C. LEONG TEO, Q. ZENG, C. LAUGIER and M. H. ANG Jr., «Controlling a Wheelchair Indoors Using Thought », IEEE Intelligent Systems, 22 (2007), n° 2, p. 18-24.

[SD06] E.W. SELLERS and E. DONCHIN, «A P300-based brain-computer interface: initial tests by ALS patients», Clin Neurophysiol., 117 (2006), n° 3, p. 538-548.

[VML+07] G. VANACKER, J.R. MILLÁN, E LEW, P.W. FERREZ, F. GALÁN MOLES, J. PHILIPS, H. VAN BRUSSEL and M. NUTTIN, «Context-Based Filtering for Assisted Brain-Actuated Wheelchair Driving », Computational Intelligence and Neuroscience, 2007 (2007), p. Article ID 25130, 12 pages.

[WBM+02] J. WOLPAW, N. BIRMAUMER, D. MCFARLAND, G. PFURTSCHELLER and T. VAUGHAN, «Brain-computer interfaces for communication and control », Clinical Neurophysiology 113 (2002), n°6, p. 767-791.

[WGWB05] M. G. WENTRUP, K. GRAMANN, E. WASCHER and M. BUSS, «EEG source localization for brain-computer-interfaces», in 2nd International IEEE EMBS Conference on Neural Engineering, 2005, p. 128-131.

[WLA+06] J. WOLPAW, G. LOEB, B. ALLISON, E. DONCHIN, O. DO NASCIMENTO, W. HEETDERKS, F. NIJBOER, W. SHAIN and J. N. TURNER, «BCI meeting 2005–workshop on signals and recording methods », IEEE Transaction on Neural Systems and rehabilitation Engineering 14 (2006), n°2, p. 138-141.

[WZL+04] Y. WANG, Z. ZHANG, Y. LI, X. GAO, S. GAO and F. YANG, «BCI competition 2003–data set IV : an algorithm based on CSSD and FDA for classifying single-trial EEG», IEEE Transactions on Biomedical Engeneering 51 (2004), n°6, p. 1081-1086.

[Zad96] L. A. ZADEH, «Fuzzy sets », Fuzzy sets, fuzzy logic, and fuzzy systems : selected papers by Lotfi A. Zadeh (1996), p. 19-34.