nips nips2006 nips2006-126 nips2006-126-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ryota Tomioka, Kazuyuki Aihara, Klaus-Robert Müller
Abstract: We propose a novel framework for the classification of single trial ElectroEncephaloGraphy (EEG), based on regularized logistic regression. Framed in this robust statistical framework no prior feature extraction or outlier removal is required. We present two variations of parameterizing the regression function: (a) with a full rank symmetric matrix coefficient and (b) as a difference of two rank=1 matrices. In the first case, the problem is convex and the logistic regression is optimal under a generative model. The latter case is shown to be related to the Common Spatial Pattern (CSP) algorithm, which is a popular technique in Brain Computer Interfacing. The regression coefficients can also be topographically mapped onto the scalp similarly to CSP projections, which allows neuro-physiological interpretation. Simulations on 162 BCI datasets demonstrate that classification accuracy and robustness compares favorably against conventional CSP based classifiers. 1
[1] J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, and T. M. Vaughan, “Braincomputer interfaces for communication and control”, Clin. Neurophysiol., 113: 767–791, 2002.
[2] N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversen, B. Kotchoubey, A. K¨bler, J. Perelu mouter, E. Taub, and H. Flor, “A spelling device for the paralysed”, Nature, 398: 297–298, 1999.
[3] G. Pfurtscheller, C. Neuper, C. Guger, W. Harkam, R. Ramoser, A. Schl¨gl, B. Obermaier, o and M. Pregenzer, “Current Trends in Graz Brain-computer Interface (BCI)”, IEEE Trans. Rehab. Eng., 8(2): 216–219, 2000.
[4] B. Blankertz, G. Curio, and K.-R. M¨ller, “Classifying Single Trial EEG: Towards Brain u Computer Interfacing”, in: T. G. Diettrich, S. Becker, and Z. Ghahramani, eds., Advances in Neural Inf. Proc. Systems (NIPS 01), vol. 14, 157–164, 2002.
[5] B. Blankertz, G. Dornhege, C. Sch¨fer, R. Krepki, J. Kohlmorgen, K.-R. M¨ller, V. Kunzmann, a u F. Losch, and G. Curio, “Boosting Bit Rates and Error Detection for the Classification of Fast-Paced Motor Commands Based on Single-Trial EEG Analysis”, IEEE Trans. Neural Sys. Rehab. Eng., 11(2): 127–131, 2003.
[6] B. Blankertz, G. Dornhege, M. Krauledat, K.-R. M¨ller, V. Kunzmann, F. Losch, and G. Cuu rio, “The Berlin Brain-Computer Interface: EEG-based communication without subject training”, IEEE Trans. Neural Sys. Rehab. Eng., 14(2): 147–152, 2006.
[7] G. Dornhege, J. del R. Mill´n, T. Hinterberger, D. McFarland, and K.-R. M¨ller, eds., Towards a u Brain-Computer Interfacing, MIT Press, 2006, in press.
[8] T. N. Lal, M. Schr¨der, T. Hinterberger, J. Weston, M. Bogdan, N. Birbaumer, and o B. Sch¨lkopf, “Support Vector Channel Selection in BCI”, IEEE Transactions Biomedical o Engineering, 51(6): 1003–1010, 2004.
[9] Z. J. Koles, “The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG”, Electroencephalogr. Clin. Neurophysiol., 79: 440–447, 1991.
[10] G. Pfurtscheller and F. H. L. da Silva, “Event-related EEG/MEG synchronization and desynchronization: basic principles”, Clin. Neurophysiol., 110(11): 1842–1857, 1999.
[11] H. Ramoser, J. M¨ ller-Gerking, and G. Pfurtscheller, “Optimal spatial filtering of single trial u EEG during imagined hand movement”, IEEE Trans. Rehab. Eng., 8(4): 441–446, 2000.
[12] N. J. Hill, J. Farquhar, T. N. Lal, and B. Sch¨lkopf, “Time-dependent demixing of task-relevant o EEG sources”, in: Proceedings of the 3rd International Brain-Computer Interface Workshop and Training Course 2006, Verlag der Technischen Universit¨t Graz, 2006. a
[13] B. Efron, “The Efficiency of Logistic Regression Compared to Normal Discriminant Analysis”, J. Am. Stat. Assoc., 70(352): 892–898, 1975.
[14] T. Minka, “Discriminative models, not discriminative training”, Tech. Rep. TR-2005-144, Microsoft Research Cambridge, 2005.
[15] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, SpringerVerlag, 2001.
[16] H. Shimodaira, “Improving predictive inference under covariate shift by weighting the loglikelihood function”, Journal of Statistical Planning and Inference, 90: 227–244, 2000.
[17] S. Sugiyama and K.-R. M¨ ller, “Input-Dependent Estimation of Generalization Error under u Covariate Shift”, Statistics and Decisions, 23(4): 249–279, 2005. (a) Subject A. CSP filter coefficients left hand right hand (c) Subject A. Logistic regression (rank=2) filter coefficients [0.67] [0.61] foot [0.70] [4.74] [3.19] [7.11] left hand [0.41] [0.33] right hand [0.59] [1.88] [2.04] [2.40] left hand (b) Subject B. CSP filter coefficients left hand foot (d) Subject B. Logistic regression (rank=2) filter coefficients Figure 2: Examples of spatial filter coefficients obtained by CSP and the rank=2 parameterized logistic regression. (a) Subject A. Some CSP filters are corrupted by artifacts. (b) Subject B. Some CSP filters are corrupted by strong occipital α-activity. (c) Subject A. Logistic regression coefficients are focusing on the physiologically expected “left hand” and “right hand” areas. (d) Subject B. Logistic regression coefficients are focusing on the “left hand” and “foot” areas. Electrode positions are marked with crosses in every plot. For CSP filters, the generalized eigenvalues (Eq. (2)) are shown inside brackets.