Motor Imagery EEG Recognition Based on WPD-CSP and KF-SVM in Brain Computer Interfaces

Abstract:

A recognition method based on Wavelet Packet Decomposition - Common Spatial Patterns (WPD-CSP) and Kernel Fisher Support Vector Machine (KF-SVM) is developed and used for EEG recognition in motor imagery brain–computer interfaces (BCIs). The WPD-CSP is used for feature extraction and KF-SVM is used for classification. The presented recognition method includes the following steps: (1) some important EEG channels are selected. The 'haar' wavelet basis is used to take wavelet packet decomposition. And some decomposed sub-bands related with motor imagery for each EEG channel are reconstructed to obtain the relevant frequency information. (2) A six-dimensional feature vector is obtained by the CSP feature extraction to the reconstructed signal. And then the within-class scatter is calculated based on the feature vector. (3) The scatter is added into the radical basis function to construct a new kernel function. The obtained new kernel is integrated into the SVM to act as its kernel function. To evaluate effectiveness of the proposed WPD-CSP + KF-SVM method, the data from the 2008 international BCI competition are processed. A preliminary result shows that the proposed classification algorithm can well recognize EEG data and improve the EEG recognition accuracy in motor imagery BCIs.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 2829-2833
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.2829
• Online since: May 2014
• Authors: Bang Hua Yang*, Ting Wu, Qian Wang, Zhi Jun Han
• Keywords: Brain Computer Interface (BCI), Common Spatial Patterns (CSP), Kernel Fisher, Support Vector Machine (SVM), Wavelet Packet Decomposition (WPD)

References

[1] J. R. Wolpaw, N. Birbaumer, D. J. McFarland, etc. Brain-computer interfaces for communication and control. Clinical neurophysiology, 113(6), (2002), p.767–791.

DOI: 10.1016/s1388-2457(02)00057-3

[2] M. Arvaneh, C.T. Guan, K. KengAng, and C. Quek. Optimizing spatial filters by minimizing within-class dissimilarities in electroencephalogram-based brain–computer Interface. IEEE Transactions on Neural Networks and Learning Systems24(4), (2013).

DOI: 10.1109/tnnls.2013.2239310

[3] G.Q. Liu, D.G. Zhang, J.J. Meng, G. Huang and X.Y. Zhu. Unsupervised adaptation of electroencephalogram signal processing based on fuzzy C-means algorithm. International Journal of Adaptive Control and Signal Processing 26, (2012), p.482–495.

DOI: 10.1002/acs.1293

[4] Q.B. Zhao, L.Q. Zhang, C. Andrzej J. Li 2008 Incremental common spatial pattern algorithm for BCI Proceedings of the International Joint Conference on Neural Networks 2656–2659.

DOI: 10.1109/ijcnn.2008.4634170

[5] M. Kaper, P. Meinicke, U. Grossekathoefer, etc. BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm, IEEE Trans. Biomed. Eng 51, (2004) p.1073–1076.

DOI: 10.1109/tbme.2004.826698

[6] R. Ksantini, B. Boufama, I. Shafiq Ahmad, etc. 2010 A New Combined KSVM and KFD Model for Classification and Recognition 2010. Fifth International Conference on Digital Information Management (ICDIM) , (2010), pp.188-193.

DOI: 10.1109/icdim.2010.5664217

[7] B.H. YANG, Z.J. Han, Q. Wang, L.F. He. A new classification method based on KF-SVM in Brain Computer Interfaces. 6th International Symposium on Computational Intelligence and Design(ISCID), Hangzhou, China, 2013, 10, 28-29. (2013), pp.193-196.

DOI: 10.1109/iscid.2013.55

[8] BCI Competition IV: http: /www. bbci. de/competition/iv.