No Access

FEATURE EXTRACTION OF MOTOR IMAGERY EEG BASED ON WAVELET TRANSFORM AND HIGHER-ORDER STATISTICS

RENHUAN YANG

Department of Instrument Science and Engineering, Southeast University, Nanjing 210096, P. R. China

Department of Biomedical Engineering, University of Minnesota, MN 55455, USA

Search for more papers by this author

AIGUO SONG

Department of Instrument Science and Engineering, Southeast University, Nanjing 210096, P. R. China

Corresponding author.

Search for more papers by this author

, and

BAOGUO XU

Department of Instrument Science and Engineering, Southeast University, Nanjing 210096, P. R. China

Search for more papers by this author

https://doi.org/10.1142/S0219691310003535Cited by:30 (Source: Crossref)

Abstract

Feature extraction plays an important role in brain-computer interface (BCI) systems. In order to characterize the motor imagery related rhythm and higher-order statistics information contained within the EEG signals, a novel feature extraction method based on harmonic wavelet transform and bispectrum is developed and applied to the recognition of right and left motor imageries for developing EEG-based BCI systems. The experimental results on the Graz BCI data set have shown that the separability of the two classes features extracted by the proposed method is notable. Its performance was evaluated by a linear discriminant analysis (LDA) classifier. The recognition accuracy of 90% was obtained. The recognition results have demonstrated the effectiveness of the proposed method. This method provides an effective way for EEG feature extraction in BCI system.

Keywords:

AMSC: 22E46, 53C35, 57S20

References

J. R. Wolpawet al., Clin. Neurophysiol. 113, 767 (2002), DOI: 10.1016/S1388-2457(02)00057-3. Crossref, Web of Science, Google Scholar
L. Kauhanenet al., IEEE Trans. Neural Syst. Rehabil. Eng. 14, 190 (2006), DOI: 10.1109/TNSRE.2006.875546. Crossref, Web of Science, Google Scholar
J. Kronegget al., IEEE Trans. Neural Syst. Rehabil. Eng. 15, 50 (2007), DOI: 10.1109/TNSRE.2007.891389. Crossref, Web of Science, Google Scholar
J. R. Wolpawet al., Clin. Neurophysiol. 113, 767 (2002), DOI: 10.1016/S1388-2457(02)00057-3. Crossref, Web of Science, Google Scholar
R. H. Yang, A. G. Song and W. J. Yuan, Mod. Phys. Lett. B 23(11), 1405 (2009), DOI: 10.1142/S0217984909019533. Link, Web of Science, Google Scholar
R. H. Yang and A. G. Song, Internat. J. Mod. Phys. B 22(30), 5365 (2008), DOI: 10.1142/S0217979208049509. Link, Web of Science, Google Scholar
M. Acharyya and M. K. Kundu, Int. J. Wavelets Multiresolut. Inf. Process. 6(3), 391 (2008), DOI: 10.1142/S0219691308002252. Link, Web of Science, Google Scholar
V. Kabeer and N. K. Narayanan, Int. J. Wavelets Multiresolut. Inf. Process. 7(5), 617 (2009), DOI: 10.1142/S0219691309003124. Link, Web of Science, Google Scholar
M. Varstaet al., Evaluating the performance of three feature sets for brain-computer interfaces with an early stopping MLP committee, 15th International Conference on Pattern Recognition (ICPR–00) (2000) pp. 2907–2910. Google Scholar
P. Mark and K. Aleksandar, Feature extraction in development of brain-computer interface: A case study, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (1998) pp. 2058–2061. Google Scholar
D. M. Brett, W. Justin and H. S. Seung, IEEE Trans. Biomed. Eng. 51, 1052 (2004). Web of Science, Google Scholar
G. Y. Chen and P. Bhattacharya, Int. J. Wavelets Multiresolut. Inf. Process. 7(2), 215 (2009), DOI: 10.1142/S0219691309002854. Link, Web of Science, Google Scholar
D. J. McFarlandet al., Brain Topogr. 12, 177 (2004), DOI: 10.1023/A:1023437823106. Crossref, Web of Science, Google Scholar
D. P. Burkeet al., IEEE Trans. Neural Syst. Rehab. Eng. 13, 12 (2004), DOI: 10.1109/TNSRE.2004.841881. Crossref, Web of Science, Google Scholar
C. W. Anderson, E. A. Stolz and S. Shamsunder, IEEE Trans. Biomed. Eng. 45, 277 (2004), DOI: 10.1109/10.661153. Crossref, Web of Science, Google Scholar
T. Wang, J. Deng and B. He, Clin. Neurophysiol. 115, 2744 (2000), DOI: 10.1016/j.clinph.2004.06.022. Crossref, Web of Science, Google Scholar
R. Q. Yan and R. X. Gao, Int. J. Wavelets Multiresolut. Inf. Process. 7(4), 411 (2009), DOI: 10.1142/S0219691309002994. Link, Web of Science, Google Scholar
H. Li, L. Q. Li and Y. Y. Tang, Int. J. Wavelets Multiresolut. Inf. Process. 5(6), 941 (2007), DOI: 10.1142/S0219691307002130. Link, Web of Science, Google Scholar
R. H. Yang, A. G. Song and B. G. Xu, J. Southeast Univ. Nat. Sci. 38(6), 996 (2008). Google Scholar
B. Abibullaev, H. D. Seo and M. S. Kim, Int. J. Wavelets Multiresolut. Inf. Process. 8(1), 33 (2010), DOI: 10.1142/S0219691310003341. Link, Web of Science, Google Scholar
M. Fatourechi, S. G. Mason and G. E. Birch, A wavelet-based approach for the extraction of event related potentials from EEG, Proc. ICASSP–04 (2004) pp. 737–740. Google Scholar
BCI Competition 2003; http://ida.first.fraunhofer.de/projects/bci/competition/ . Google Scholar
B. Blankertzet al., IEEE Trans. Biomed. Eng. 51(6), 1044 (2004), DOI: 10.1109/TBME.2004.826692. Crossref, Web of Science, Google Scholar
R. H. Yang and A. G. Song, Internat. J. Mod. Phys. C 20(5), 781 (2009), DOI: 10.1142/S012918310901400X. Link, Web of Science, Google Scholar
Z. T. Huang and Q. G. Yang, Nonlinear Anal. Real World Appl. 11, 592 (2010), DOI: 10.1016/j.nonrwa.2008.11.007. Crossref, Web of Science, Google Scholar
E. Houdayeret al., Clin. Neurophysiol. 117, 628 (2006), DOI: 10.1016/j.clinph.2005.12.001. Crossref, Web of Science, Google Scholar
G. Pfurtscheller and F. H. Lopes da Silva, Clin. Neurophysiol. 110, 1842 (1999), DOI: 10.1016/S1388-2457(99)00141-8. Crossref, Web of Science, Google Scholar
D. E. Newland, Proc. Roy. Soc. Lond. A 443, 203 (1993). Crossref, Web of Science, Google Scholar
N. Taikang and J. D. Bronzino, Ann. Biomed. Eng. 26, 688 (1998). Web of Science, Google Scholar
S. M. Zhou, J. Q. Gan and F. Sepulveda, Inform. Sci. 178, 1629 (2008), DOI: 10.1016/j.ins.2007.11.012. Crossref, Web of Science, Google Scholar
R. Subba , An Introduction to Bispectral Analysis and Bilinear Time Series Models ( Springer-Verlag , New York , 1984 ) . Google Scholar
A. Swami and G. B. Giannakis, Signal Process. 53, 89 (1996), DOI: 10.1016/0165-1684(96)00099-0. Crossref, Web of Science, Google Scholar
M. R. Raghuveer and C. L. Nikias, IEEE Trans. Acoust. Speech Signal Process. 33, 1213 (1985), DOI: 10.1109/TASSP.1985.1164679. Crossref, Google Scholar
D. E. Newland, ASME J. Vib. Acoustics 116, 409 (1994), DOI: 10.1115/1.2930443. Crossref, Web of Science, Google Scholar
D. E. Newland, Proc. R. Soc. Lond. A 444, 605 (1994). Crossref, Web of Science, Google Scholar
M. R. Raghuveer and C. L. Nikias, IEEE Trans. Acoust. Speech Signal Process. 33, 1213 (1985), DOI: 10.1109/TASSP.1985.1164679. Crossref, Google Scholar
R. R. Mysore and L. N. Chrysostomos, Signal Process. 10, 35 (1986). Web of Science, Google Scholar
G. S. Hu, Digital Signal Processing (Tsinghua University Press, 2003) pp. 552–554. Google Scholar
W. S. Chenet al., Int. J. Wavelets Multiresolut. Inf. Process. 7(2), 199 (2009), DOI: 10.1142/S0219691309002878. Link, Web of Science, Google Scholar
R. A. Fisher, Ann. Eugen. 7, 179 (1936). Crossref, Google Scholar
H. Chen, L. Q. Li and Y. Y. Tang, Int. J. Wavelets Multiresolut. Inf. Process. 7(3), 375 (2009), DOI: 10.1142/S0219691309002970. Link, Web of Science, Google Scholar
B. G. Xu and A. G. Song, J. Biomed. Sci. Eng. 1, 64 (2008), DOI: 10.4236/jbise.2008.11010. Crossref, Web of Science, Google Scholar