Improving Mental Task Classification by Adding High Frequency Band Information
- 296 Downloads
Features extracted from delta, theta, alpha, beta and gamma bands spanning low frequency range are commonly used to classify scalp-recorded electroencephalogram (EEG) for designing brain–computer interface (BCI) and higher frequencies are often neglected as noise. In this paper, we implemented an experimental validation to demonstrate that high frequency components could provide helpful information for improving the performance of the mental task based BCI. Electromyography (EMG) and electrooculography (EOG) artifacts were removed by using blind source separation (BSS) techniques. Frequency band powers and asymmetry ratios from the high frequency band (40–100 Hz) together with those from the lower frequency bands were used to represent EEG features. Finally, Fisher discriminant analysis (FDA) combining with Mahalanobis distance were used as the classifier. In this study, four types of classifications were performed using EEG signals recorded from four subjects during five mental tasks. We obtained significantly higher classification accuracy by adding the high frequency band features compared to using the low frequency bands alone, which demonstrated that the information in high frequency components from scalp-recorded EEG is valuable for the mental task based BCI.
KeywordsBCI EEG High frequency band EMG Mental task
The authors would like to thank the anonymous reviewers for their valuable comments.
- 1.Vaughan, T. M., Heetderks, W. J., Trejo, L. J., Rymer, W. Z., Weinrich, M., Moore, M. M. et al, Guest editorial brain–computer interface technology: a review of the second international meeting. IEEE Trans. Neural Syst. Rehabil. Eng. 11:94–109, 2003. doi: 10.1109/TNSRE.2003.814799.CrossRefGoogle Scholar
- 6.Anderson, C. W., Devulapalli, S. V., and Stolz, E. A., EEG Signal classification with different signal representations, In: Proc. IEEE Workshop on Neural Networks for Signal Processing, pp. 475–483 Aug. 31–Sept. 2 1995.Google Scholar
- 10.Li, Z. W., and Shen, M. F., Classification of mental task EEG signals using wavelet packet entropy and SVM. In: Proc. 8th Int. Conf. on Electronic Measurement and Instruments, Xian, China, pp. 906–909 Aug. 16–July 18 2007.Google Scholar
- 11.Liu, H., Wang, J., and Zheng, C., Mental tasks classification and their EEG structures analysis by using the growing hierarchical self-organizing map. In: Proc. 1st Int. Conf. on Neural Interface and Control, Wuhan, China, pp. 115–118 May 26–28, 2005.Google Scholar
- 13.Palaniappan, R., Brain computer interface design using band powers extracted during mental tasks. In: Proc. 2nd Int. IEEE EMBS Conf. on Neural Eng., Arlington, Virginia, pp. 321–324, Mar. 16–19, 2005.Google Scholar
- 22.Whitham, E. M., Pope, K. J., Fitzgibbon, S. P., Lewis, T., Clark, C. R., Loveless, S., Broberg, M., Wallace, A., DeLosAngeles, D., Lillie, P., Hardy, A., Fronsko, R., Pulbrook, A., and Willoughby, J. O., Sclap electrical recording during paralysis: Quantitative evidence that EEG frequencies above 20 Hz are contaminated by EMG. Clin. Neurophysiol. 118:1877–1888, 2007. doi: 10.1016/j.clinph.2007.04.027.CrossRefGoogle Scholar
- 25.Li, R., and Principe, J. C., Blinking Artifact removal in cognitive EEG data using ICA. In: Proc. 28th Int. IEEE EMBS Conf., New York City, USA, pp. 5273–5276, Aug. 30–Sept. 3, 2006.Google Scholar
- 28.Xue, Z. J., Li, J., Li, S., and Wan, B. k., Using ICA to remove eye blink and power line artifacts in EEG. In: Proc. First Int. Conf. on Innovative Computing, Information and Control, Beijing, China, pp. 107–110, Aug. 2006.Google Scholar
- 29.Zhou, W., Zhou, J., Zhao, H., and Ju, L., Removing eye movement and power line artifacts from the EEG based on ICA. In: Proc. 27th Int. IEEE EMBS Conf., Shanghai, China, pp. 6017–6020, Sep.1–4, 2005.Google Scholar
- 34.Hu, G. S., Digital signal processing: theory, algorithm and implementation. Tsinghua University Press, Beijing, 1997.Google Scholar