Selecting Filter Range of Hybrid Brain-Computer Interfaces by Mutual Information

Abstract:

The hybrid brain-computer interface (BCI) based on electroencephalography (EEG) become more and more popular. Motor imagery, steady state visual evoked potentials (SSVEPs) and P300 are main training Paradigms. In our previous research, BCI systems based on motor imagery can be extended by speech imagery. However, noise and artifact may be produced by different mental tasks and EEG signals are also different among users, so the classification accuracy can be improved by selecting optimum frequency range for each user. Mutual information (MI) is usually used to choose optimal features. After extracted the features from each narrow frequency range of EEG by common spatial patterns (CSP), the features are assessed by MI. Then, the optimum frequency range can be acquired. The final classification results are calculated by support vector machine (SVM). The average result of optimum frequency range from seven subjects is better than the result of a fixed frequency range.

• Periodical: Advanced Materials Research (Volume 981)
• Pages: 171-174
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.981.171
• Online since: July 2014
• Authors: Li Wang*, Xiong Zhang, Xue Fei Zhong, Zhao Wen Fan
• Keywords: Brain Computer Interface (BCI), Common Spatial Patterns (CSP), Mutual Information (MI), Support Vector Machine (SVM)

References

[1] J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller and T. M. Vaughan: Clin. Neurophysiol., Vol. 113 (2002), p.767–791.

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

[2] D. McFarland, D. Krusienski, W. Sarnacki and J. Wolpaw: J. Neural Eng., Vol. 5 (2008), pp.101-110.

[3] G. Pfurtscheller, C. Brunner, A. Schlögl and F. H. Lopes da Silva: NeuroImage, Vol. 31 (2006), pp.153-159.

DOI: 10.1016/j.neuroimage.2005.12.003

[4] P. Lee, C. Yeh, J. Y. Cheng, C. Yang and G. Lan: IEEE Trans. Biomed. Eng., Vol. 58 (2011), pp.3350-3359.

[5] M. Salvaris, C. Cinel, L. Citi and R. Poli: IEEE Trans. Neural Syst. Rehabil. Eng., Vol. 20 (2012), pp.8-17.

DOI: 10.1109/tnsre.2011.2174463

[6] Y. Li, J. Pan, F. Wang and Z. Yu: IEEE Trans. Biomed. Eng., Vol. 60(11) (2013), pp.3156-3166.

[7] L. Wang, X. Zhang, X. Zhong and Y. Zhang: Biomedical Signal Processing and Control, Vol. 8 (2013), pp.901-908.

[8] L. Wang, X. Zhang and Y. Zhang, in: Proceedings of the 35rd Annual Conference of the IEEE Engineering in Medicine and Biology Society, Osaka, Japan (2013), pp.7056-7059.

[9] H. Ramoser, J. Müller-Gerking and G. Pfurtscheller: IEEE Trans. Rehabil. Eng., Vol. 8 (2000), pp.441-446.

[10] R. Battiti: IEEE Trans. Neural Networks, Vol. 5(4) (1994), pp.537-550.

[11] H. Zhang, Z. Y. Chin, K. K. Ang, C. Guan and C. Wang: IEEE Trans. Neural Networks, Vol. 22(1) (2011), pp.52-63.

[12] Information on http: /www. csie. ntu. edu. tw/cjlin/libsvm.