A regularized discriminative framework for EEG analysis with application to brain-computer interface

NeuroImage

Volumn 49, Issue 1, 2010, Pages 415-432

  Tomioka, Ryota ^a,b,c   Müller, Klaus Robert ^c,d  

^a UNIVERSITY OF TOKYO   (Japan)

^b TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^c TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

^d Bernstein Center for Computational Neuroscience   (Germany)

Author keywords

Brain computer interface; Convex optimization; Discriminative learning; Discriminative modeling of brain imaging signals; Dual spectral norm; Group lasso; P300 speller; Regularization; Spatio temporal factorization; Trace norm

Indexed keywords

ARTICLE; BRAIN COMPUTER INTERFACE; CLASSIFIER; CONTROLLED STUDY; DISCRIMINATION LEARNING; ELECTROENCEPHALOGRAPHY; LEARNING ALGORITHM; MACHINE LEARNING; NEUROIMAGING; NEUROPHYSIOLOGY; PRIORITY JOURNAL; PROCESS OPTIMIZATION; SIGNAL PROCESSING; TASK PERFORMANCE;

ALGORITHMS; BRAIN; DISCRIMINATION LEARNING; ELECTROENCEPHALOGRAPHY; EVENT-RELATED POTENTIALS, P300; FINGERS; HUMANS; LOGISTIC MODELS; MODELS, STATISTICAL; SIGNAL PROCESSING, COMPUTER-ASSISTED; USER-COMPUTER INTERFACE;

EID: 70349969800     PISSN: 10538119     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neuroimage.2009.07.045     Document Type: Article

References (72)

1. Abernethy, J., Bach, F., Evgeniou, T., Vert, J.-P., September 2006. Low-rank matrix factorization with attributes. Tech. Rep. N-24/06/MM, Ecole des mines de Paris, France.
2. Amit Y., Fink M., Srebro N., and Ullman S. Uncovering shared structures in multiclass classification. ICML '07: Proceedings of the 24th International Conference on Machine learning (2007), ACM Press, New York, NY, USA 17-24
3. Andrew G., and Gao J. Scalable training of L1-regularized log-linear models. Proc. of the 24th International Conference on Machine learning (2007), ACM, New York, NY, USA 33-40
4. Argyriou A., Evgeniou T., and Pontil M. Multi-task feature learning. In: Schölkopf B., Platt J., and Hoffman T. (Eds). Advances in Neural Information Processing Systems 19 (2007), MIT Press, Cambridge, MA 41-48
5. Argyriou A., Micchelli C.A., Pontil M., and Ying Y. A spectral regularization framework for multi-task structure learning. In: Platt J., Koller D., Singer Y., and Roweis S. (Eds). Advances in Neural Information Processing Systems 20 (2008), MIT Press, Cambridge, MA 25-32
6. Birbaumer N., Ghanayim N., Hinterberger T., Iversen I., Kotchoubey B., Kübler A., Perelmouter J., Taub E., and Flor H. A spelling device for the paralysed. Nature 398 (1999) 297-298
7. Bishop C.M. Pattern Recognition and Machine Learning (2007), Springer
8. Blankertz B., Curio G., and Müller K.-R. Classifying single trial EEG: Towards brain computer interfacing. In: Diettrich T.G., Becker S., and Ghahramani Z. (Eds). Advances in Neural Inf. Proc. Systems (NIPS 01) Vol. 14 (2002) 157-164
9. Blankertz B., Müller K.-R., Curio G., Vaughan T.M., Schalk G., Wolpaw J.R., Schlögl A., Neuper C., Pfurtscheller G., Hinterberger T., Schröder M., and Birbaumer N. The BCI competition 2003: Progress and perspectives in detection and discrimination of EEG single trials. IEEE Trans. Biomed. Eng. 51 6 (2004) 1044-1051
10. Blankertz B., Dornhege G., Krauledat M., Müller K.R., Kunzmann V., Losch F., and Curio G. The Berlin brain-computer interface: EEG-based communication without subject training. IEEE Trans. Neural Sys. Rehab. Eng. 14 2 (2006) 147-152
11. Blankertz B., Müller K.-R., Krusienski D., Schalk G., Wolpaw J.R., Schlögl A., Pfurtscheller G., Millán J.d.R., Schröder M., and Birbaumer N. The BCI competition III: Validating alternative approaches to actual BCI problems. IEEE Trans. Neural Sys. Rehab. Eng. 14 2 (2006) 153-159. http://www.bbci.de/competition/iii/ see also the webpage: http://www.bbci.de/competition/iii/
12. Blankertz B., Dornhege G., Krauledat M., Müller K.-R., and Curio G. The non-invasive Berlin brain-computer interface: fast acquisition of effective performance in untrained subjects. NeuroImage 37 2 (2007) 539-550
13. Blankertz B., Tomioka R., Lemm S., Kawanabe M., and Müller K.-R. Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Proc. Magazine 25 1 (2008) 41-56
14. Boyd S., and Vandenberghe L. Convex Optimization (2004), Cambridge University Press
15. Christoforou C., Sajda P., and Parra L.C. Second order bilinear discriminant analysis for single trial EEG analysis. In: Platt J., Koller D., Singer Y., and Roweis S. (Eds). Advances in Neural Information Processing Systems 20 (2008), MIT Press, Cambridge, MA 313-320
16. Cotter S.F., Rao B.D., Engan K., and Kreutz-Delgado K. Sparse solutions to linear inverse problems with multiple measurement vectors. IEEE Trans. Signal Process 53 7 (2005) 2477-2488
17. Curran E.A., and Stokes M.J. Learning to control brain activity: a review of the production and control of EEG components for driving brain-computer interface (BCI) systems. Brain Cogn. 51 (2003) 326-336
18. Dornhege G., Blankertz B., Curio G., and Müller K.-R. Boosting bit rates in non-invasive EEG single-trial classifications by feature combination and multi-class paradigms. IEEE Trans. Biomed. Eng. 51 6 (Jun. 2004) 993-1002
19. Dornhege G., Blankertz B., Krauledat M., Losch F., Curio G., and Müller K.-R. Combined optimization of spatial and temporal filters for improving brain-computer interfacing. IEEE Trans. Biomed. Eng. 53 11 (2006) 2274-2281
20. In: Dornhege G., Millán J.d.R., Hinterberger T., McFarland D., and Müller K.-R. (Eds). Towards Brain-Computer Interfacing (2007), MIT Press
21. Dyrholm, M., Parra, L.C., 2006. Smooth bilinear classification of EEG. In: Proceedings of the IEEE 2006 International Conference of the Engineering in Medicine and Biology Society.
22. Dyrholm M., Christoforou C., and Parra L.C. Bilinear discriminant component analysis. J. Mach. Learn. Res. 8 (2007) 1097-1111
23. Faraut J., and Koranyi A. Analysis on Symmetric Cones (1995), Oxford University Press
24. Farquhar, J., Hill, J., Schölkopf, B., 2006. Learning optimal EEG features across time, frequency and space. In NIPS 2006 workshop Current Trends in Brain-Computer Interfacing.
25. Farwell L., and Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr. Clin. Neurophysiol. 70 6 (1988) 510-523
26. Fazel, M., Hindi, H., Boyd, S.P., 2001. A Rank minimization heuristic with application to minimum order system approximation. In: Proceedings of the American Control Conference.
27. Fukunaga K. Introduction to Statistical Pattern Recognition. 2nd Edition (1990), Academic Press, Boston
28. Harshman R. Foundations of the PARAFAC procedure: models and conditions for an "explanatory" multi-modal factor analysis. UCLA Work. Pap. Phon. 16 (1970) 1-84
29. Hastie T., Tibshirani R., and Friedman J. The Elements of Statistical Learning (2001), Springer, Verlag
30. Haufe, S., Nikulin, V.V., Ziehe, A., Müller, K.-R., Nolte, G., 2008. Combining sparsity and rotational invariance in EEG/MEG source reconstruction. NeuroImage 42 (2), 726-738.
31. Haynes J.D., and Rees G. Decoding mental states from brain activity in humans. Nat. Rev. Neurosci. 7 7 (2006) 523-534
32. Hill J., Farquhar J., Martens S., Bieβmann F., and Schölkopf B. Effects of stimulus type and of errorcorrecting code design on bci speller performance. In: Koller D., Schuurmans D., Bengio Y., and Bottou L. (Eds). Advances in Neural Information Processing Systems 21 (2009), MIT Press, Cambridge, MA 665-672
33. Hochberg L.R., Serruya M.D., Friehs G.M., Mukand J.A., Saleh M., Caplan A.H., Branner A., Chen D., Penn R.D., and Donoghue J.P. Neuronal ensemble control of prosthetic devices by a human with tetraplegia. Nature 442 (2006) 164-171
34. Hyvärinen A., Karhunen J., and Oja E. Independent Component Analysis (2001), Wiley Interscience
35. Kim Y., Kim J., and Kim Y. Blockwise sparse regression. Stat. Sinica 16 (2006) 375-390
36. Koles Z.J. The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG. Electroencephalogr. Clin. Neurophysiol. 79 (1991) 440-447
37. Krusienski D., Sellers E., McFarland D., Vaughan T., and Wolpaw J. Toward enhanced P300 speller performance. J. Neurosci. Meth. 167 1 (2008) 15-21
38. Kübler A., Kotchoubey B., Kaiser J., Wolpaw J., and Birbaumer N. Brain-computer communication: unlocking the locked in. Psychol. Bull. 127 3 (2001) 358-375
39. Lemm S., Blankertz B., Curio G., and Müller K.-R. Spatio-spectral filters for improved classification of single trial EEG. IEEE Trans. Biomed. Eng. 52 9 (2005) 1541-1548
40. MacKay D.J. Information Theory, Inference and Learning Algorithms (2003), Cambridge University Press
41. Mørup M., Hansen L.K., Arnfred S.M., Lim L., and Madsen K.H. Shift invariant multilinear decomposition of neuroimaging data. NeuroImage 42 4 (2008) 1439-1450
42. Nicolelis M.A.L. Brain-machine interfaces to restore motor function and probe neural circuits. Nat. Rev. Neurosci. 4 5 (2003) 417-422
43. Nocedal J., and Wright S. Numerical Optimization (1999), Springer
44. Parra L., Alvino C., Tang A.C., Pearlmutter B.A., Yeung N., Osman A., and Sajda P. Linear spatial integration for single trial detection in encephalography. NeuroImage 7 1 (2002) 223-230
45. Parra L.C., Spence C.D., Gerson A.D., and Sajda P. Recipes for the linear analysis of EEG. NeuroImage 28 2 (2005) 326-341
46. Parra L., Christoforou C., Gerson A., Dyrholm M., Luo A., Wagner M., Philiastides M., and Sajda P. Spatiotemporal linear decoding of brain state. IEEE Signal Process Mag. 25 1 (2008) 107-115
47. Penny W.D., Roberts S.J., Curran E.A., and Stokes M.J. EEG-based communication: a pattern recognition approach. IEEE Trans. Rehab. Eng. 8 2 (June 2000) 214-215
48. Pfurtscheller G., and da Silva F.H.L. Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin. Neurophysiol. 110 11 (Nov 1999) 1842-1857
49. Pfurtscheller G., Neuper C., Guger C., Harkam W., Ramoser R., Schlögl A., Obermaier B., and Pregenzer M. Current trends in Graz brain-computer interface (BCI). IEEE Trans. Rehab. Eng. 8 2 (June 2000) 216-219
50. Pfurtscheller G., Müller-Putz G.R., Schlögl A., Graimann B., Scherer R., Leeb R., Brunner C., Keinrath C., Lee F., Townsend G., Vidaurre C., and Neuper C. 15 years of BCI research at Graz University of Technology: current projects. IEEE Trans. Neural Sys. Rehab. Eng. 14 2 (June 2006) 205-210
51. Rakotomamonjy A., and Guigue V. BCI Competition III : Dataset II - Ensemble of SVMs for BCI P300 speller. IEEE Trans. Biomed. Eng. 55 3 (2008) 1147-1154
52. Ramoser H., Müller-Gerking J., and Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. Rehab. Eng. 8 4 (2000) 441-446
53. Recht, B., Fazel, M., Parrilo, P.A., June 2007. Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization. Tech. Rep. arXiv:0706.4138v1 [math.OC].
54. Rennie J.D.M., and Srebro N. Fast maximum margin matrix factorization for collaborative prediction. ICML '05: Proceedings of the 22nd International Conference on Machine learning (2005), ACM Press, New York, NY, USA 713-719
55. Schalk G., Wolpaw J.R., McFarland D.J., and Pfurtscheller G. EEG-based communication: presence of an error potential. Clin. Neurophysiol. 111 12 (2000) 2138-2144
56. Srebro, N., 2004. Learning with Matrix Factorizations. Ph.D. thesis, Massachusetts Institute of Technology.
57. Srebro N., Rennie J.D.M., and Jaakkola T.S. Maximum-margin matrix factorization. In: Saul L.K., Weiss Y., and Bottou L. (Eds). Advances in Neural Information Processing Systems 17 (2005), MIT Press, Cambridge, MA 1329-1336
58. Tibshirani R. Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Series B 58 1 (1996) 267-288
59. Tikhonov A.N., and Arsenin V.Y. Solutions of Ill-Posed Problems (1977), V. H. Winston & Sons
60. Tomioka R., and Aihara K. Classifying matrices with a spectral regularization. ICML '07: Proceedings of the 24th International Conference on Machine learning (2007), ACM Press 895-902
61. Tomioka, R., Sugiyama, M., 2008. Sparse learning with duality gap guarantee. In NIPS 2008 workshop Optimization for Machine Learning.
62. Tomioka, R., Sugiyama, M., in press. Dual Augmented Lagrangian Method for Efficient Sparse Reconstruction. IEEE Signal Processing Letters.
63. Tomioka R., Dornhege G., Nolte G., Aihara K., and Müller K.-R. Optimizing Spectral Filters for Single Trial EEG Classification. Lecture Notes in Computer Science Vol. 4174 (2006), Springer Berlin, Heidelberg 414-423
64. Tomioka, R., Dornhege, G., Nolte, G., Blankertz, B., Aihara, K., Müller, K.-R., July 2006b. Spectrally weighted common spatial pattern algorithm for single trial EEG classification. Tech. Rep. METR-2006-40, Department of Mathematical Informatics, University of Tokyo.
65. Tomioka R., Aihara K., and Müller K.-R. Logistic regression for single trial eeg classification. In: Schölkopf B., Platt J., and Hoffman T. (Eds). Advances in Neural Information Processing Systems 19 (2007), MIT Press, Cambridge, MA 1377-1384
66. Vapnik V.N. Statistical Learning Theory (1998), Wiley-Interscience
67. Wang Y., Zhang Z., Li Y., Gao X., Gao S., and Yang F. BCI competition 2003-data set IV: An algorithm based on CSSD and FDA for classifying single-trial EEG. IEEE Trans. Biomed. Eng. 51 6 (2004) 1081-1086
68. Wolpaw J.R., Birbaumer N., McFarland D.J., Pfurtscheller G., and Vaughan T.M. Brain-computer interfaces for communication and control. Clin. Neurophysiol. 113 (2002) 767-791
69. Wu W., Gao X., Hong B., and Gao S. Classifying single-trial EEG during motor imagery by iterative spatio-spectral patterns learning (ISSPL). IEEE Trans. Biomed. Eng. 55 6 (2008) 1733-1743
70. Yu, J., Vishwanathan, S.V.N., Günter, S., Schraudolph, N.N., 2008. A Quasi-Newton Approach to Nonsmooth Convex Optimization. ArXiv:0804.3835v3 [stat.ML].
71. Yuan M., and Lin Y. Model selection and estimation in regression with grouped variables. J. R. Stat. Soc. Series B 68 1 (2006) 49-67
72. Yuan M., Ekici A., Lu Z., and Monteiro R. Dimension reduction and coefficient estimation in multivariate linear regression. J. R. Stat. Soc. Series B 69 3 (2007) 329-346