nips nips2009 nips2009-184 nips2009-184-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Wenming Zheng, Zhouchen Lin
Abstract: The method of common spatio-spectral patterns (CSSPs) is an extension of common spatial patterns (CSPs) by utilizing the technique of delay embedding to alleviate the adverse effects of noises and artifacts on the electroencephalogram (EEG) classification. Although the CSSPs method has shown to be more powerful than the CSPs method in the EEG classification, this method is only suitable for two-class EEG classification problems. In this paper, we generalize the two-class CSSPs method to multi-class cases. To this end, we first develop a novel theory of multi-class Bayes error estimation and then present the multi-class CSSPs (MCSSPs) method based on this Bayes error theoretical framework. By minimizing the estimated closed-form Bayes error, we obtain the optimal spatio-spectral filters of MCSSPs. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on the BCI competition 2005 data set. The experimental results show that our method significantly outperforms the previous multi-class CSPs (MCSPs) methods in the EEG classification.
[1] B. Blankertz, G. Curio, & K.-R. M¨ ller (2002) Classifying single trial EEG: towards brain computer u interfacing. In: T.G. Dietterich, S. Bechker, Z. Ghaharamani (Eds.), Advances in Neural Information Processing Systems14, pp.157-164. Cambridge, MA:MIT Press.
[2] H. Ramoser, J. Mueller-Gerking, & G. Pfurtscheller (2000) Optimal spatial filtering of single trial EEG during imaged hand movement. IEEE Transactions on Rehabilitation Engineering. 8(4):441-446. 8
[3] S. Lemm, B. Blanketz, G. Curio, & K.-R. M¨ ller (2005) Spatio-spectral filters for improved classification u of single trial EEG. IEEE Transactions on Biomedical Engineering. 52(9):1541-1548.
[4] G. Dornhege, B. Blankertz, G. Curio, & K.-R. M¨ ller (2004) Boosting bit rates in noninvasive EEG singleu trial classifications by feature combination and multiclass paradigms. IEEE Transactions on Biomedical Engineering. 51(6):993-1002.
[5] M. Grosse-Wentrup, & M. Buss (2008) Multiclass Common Spatial Patterns and Information Theoretic Feature Extraction. IEEE Transactions on Biomedical Engineering. 55:1991-2000.
[6] L. C. Parra, C. D. Spence, A. D. Gerson, & P. Sajda (2005) Recipes for linear analysis of EEG. Neuroimage, 28:326-341.
[7] K. Fukunaga (1990) Introduction to Statistical Pattern Recognition (Second Edition). New York: Academic Press.
[8] J.T. Chu & J.C. Chuen (1967) Error Probability in Decision Functions for Character Recognition. Journal of the Association for Computing Machinery. 14(2):273-280.
[9] W. Zheng (2009) Heteroscedastic Feature Extraction for Texture Classification. IEEE Signal Processing Letters, 16(9):766-769.
[10] W. Zheng, H. Tang, Z. Lin, & T.S. Huang (2009) A Novel Approach to Expression Recognition from Non-frontal Face Images. Proceedings of 2009 IEEE International Conference on Computer Vision (ICCV2009), pp.1901-1908.
[11] G. Blankertz, K.R. Mueller, D. Krusienski, G. Schalk, J.R. Wolpaw, A. Schloegl, G. Pfurtscheller, J. R. Millan, M. Schroeder, & N. Birbaumer (2006) The BCI competition III: Validating alternative approaches to actual BCI problems. IEEE Transactions on Rehabilitation Engineering 14:153-159. 9