ECoG Classification Research Based on Wavelet Variance and Probabilistic Neural Network

Abstract:

For a typical ECoG-based brain-computer interface system that the subjects task is to imagine movements of either the left small finger or the tongue, a feature extraction algorithm using wavelet variance was proposed. Firstly the wavelet transform was discussed, and the definition and significance of wavelet variance were bring out and taken as feature, 6 channels with most distinctive features were selected from 64 channels for analysis; consequently the EEG data were decomposed using db4 wavelet, the wavelet coefficients variances containing Mu rhythm and Beta rhythm were taken out as features based on ERD/ERS phenomenon, and the features were classified by probabilistic neural network under a optimal spread with an algorithm of cross validation. The result of off-line showed high average classification accuracies of 89.21% and 88% for training and test data were achieved, the wavelet variance has characteristics of more simple and effective and it is suitable for feature extraction in BCI research.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 2280-2285
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.2280
• Online since: August 2013
• Authors: Shi Yu Yan, De Jun Guan
• Keywords: Brain Computer Interface (BCI), Cross-Validation, Electrocorticogram, Probabilistic Neural Network, Wavelet Variance

References

[1] Wolpaw J R, Birbaumer N, McFarland D J, et al. Brain-computer interface for communication and control, Clinical Neurophysiology, vol. 113, pp.767-791, (2002).

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

[2] Van Gerven M, Farquhar J, Schaefer R, et al. The brain-computer interface cycle, J Neural Eng, vol. 6, pp.1-10, (2009).

[3] Blankertz B, Muller K-R, Krusienski D J, et al. The BCI competition III: validating alternative approaches to actual BCI problems, IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 14, pp.153-159, (2006).

DOI: 10.1109/tnsre.2006.875642

[4] Kanoh S, Miyamoto K, Yoshinobu T. Towards an EEG-based BCI controlled by expectation, Proceeding of the 5th Internal Brain-Computer Interface Conference 2011, pp.84-87, (2011).

[5] Wilson J A, Felton E A, Garell P C, et al. ECoG factors underlying multimodal control of a brain-computer interface, IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 14, pp.246-250, (2006).

DOI: 10.1109/tnsre.2006.875570

[6] Leuthardt E C, Schalk G, Wolpaw J, et al. A brain-computer interface using electrocorticographic signals in humans, Journal of Neural Engineering, Vol. 1, pp: 63-71, (2004).

DOI: 10.1088/1741-2560/1/2/001

[7] Lal T N, Hinterberger T, Widman G, et al. Methods towards invasive human brain computer interfaces, Advances in Neural Information Processing System(NIPS), Vol. 17, pp: 737-744, (2005).

[8] Pistohl T, Ball T, Schulze-Bonhage A, et al. Prediction of arm movement trajectories from ECoG-recordings in humans, Journal of Neuroscience Methods, Vol. 167, pp: 105-114, (2008).

DOI: 10.1016/j.jneumeth.2007.10.001