Abstract
Rehabilitation technology based on brain-computer interface (BCI) has become a promising approach for patients with dyskinesia to regain movement. In this paper, a novel classification algorithm is proposed based on the characteristic of electroencephalogram (EEG) signals. Specifically wavelet packet decomposition (WPD) and Extreme learning machine with kernel (ELM_Kernel) algorithm are studied. In view of the existence of cross-banding of WPD, the average energy of the wavelet packets of the corresponding frequency bands which belong to the mu and beta rhythm are used to form the feature vectors that are classified by the ELM_Kernel algorithm. Simulation results demonstrate that the proposed algorithm produces a high probability of correct classification of 97.8% and outperforms state-of-the-art algorithms such as ELM, BP and SVM in terms of both training time and classification accuracy.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS0146411619050079/MediaObjects/11950_2019_7146_Fig1_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS0146411619050079/MediaObjects/11950_2019_7146_Fig2_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS0146411619050079/MediaObjects/11950_2019_7146_Fig3_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS0146411619050079/MediaObjects/11950_2019_7146_Fig4_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS0146411619050079/MediaObjects/11950_2019_7146_Fig5_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS0146411619050079/MediaObjects/11950_2019_7146_Fig6_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS0146411619050079/MediaObjects/11950_2019_7146_Fig7_HTML.gif)
Similar content being viewed by others
REFERENCES
Vaughan, T.M. and Wolpaw, J.R., The third international meeting on brain-computer interface technology: Making a difference, IEEE Trans. Neural Syst. Rehabil. Eng., 2006, vol. 14, pp. 126–127.
Ming, D., Wang, K., He, F., Qi, H.Z., and Wan, B.K., Study on physiological information detection and application evoked by motor imagery: Review and prospect, Chin. J. Sci. Instrum., 2014, vol. 35, no. 9, pp. 1921–1931.
Pfurtscheller, G., Putz, G.R.M., Schlogl, A., Graimann, B., Scherer, R., Leeb, R., Brunner, C., Keinrath, C., Lee, F., Townsend, G., Vidaurre, C., and Neuper, C., 15 Years of BCI research at Graz University of Technology: Current projects, IEEE Trans. Neural Syst. Rehabil. Eng., 2006, vol. 14, no. 2, pp. 205–210.
Lin, L. and Wei, Q.G., Application of CSSD and AAR in EEG signal processing, Commun. Technol., 2009, vol. 42, no. 2, pp. 207–210.
Liu, C., Zhao, H.B., Li, C.S., and Wang, H., CSP/SVM-based EEG classification of imagined hand movements, J. Northeast. Univ.(Nat. Sci.), 2010, vol. 31, no. 8, pp. 1098–1101.
Yang, Y., Si, Y.J., and Song, X.Y., ST segment classification of ECG signals based on wavelet transform and support vector machine, J. Jilin Univ. (Inf. Sci. Ed.), 2016, vol. 34, no. 3, pp. 315–319.
Yan, S.Y., Liu, C., Zhao, H.B., and Wang, H., Imaginary EEG feature extraction based on wavelet packet decomposition, Chin. J. Sci. Instrum., 2012, vol. 33, no. 8, pp. 1748–1752.
Li, M.A., Lin, L., and Yang, J.F., Adaptive feature extraction based on best on best basis of wavelet packet for motor imagery EEG, Comput. Measur. Control, 2011, vol. 19, no. 11, pp. 2755–2758, 2762.
Wang, D., Miao, D.Q., and Wang, R.Z., A new method of EEG classification with feature extraction based on wavelet packet decomposition, Acta Electron. Sin., 2013, vol. 41, no. 1, pp. 193–198.
Wang, S.Y., Zhu, G.X., and Tang, Y.Y., Feature extraction using best wavelet packet transform, Acta Electron. Sin., 2003, vol. 31, no. 7, pp. 1035–1038.
Huang, G.B., Zhu, Q.Y., and Siew, C.K., Extreme learning machine: Theory and applications, Neurocomputing, 2006, vol. 70, pp. 489–501.
Huang, G.B., Zhou, H.M., Ding, X.J., and Zhang, R., Extreme learning machine for regression and multiclass classification, IEEE Trans. Syst. Man Cybern.,Part B (Cyben.), 2012, vol. 42, no. 2, pp. 513–529.
Liang, N.Y., Saratchandran, P., Huang, G.B., and Sundararajan, N., Classification of mental tasks from EEG signals using extreme learning machine, Int. J. Neural Syst., 2006, vol. 16, no. 1, pp. 29–38.
Yuan, Q., Zhou, W.D., Li, S.F., and Cai, D.M., Approach of EEG detection based on ELM and approximate entropy, Chin. J. Sci. Instrum., 2012, vol. 33, no. 3, pp. 514–519.
Huang, Z.Y., Yu, Y.L., Gu, J., and Liu, H.P., An efficient method for traffic sign recognition based on extreme learning machine, IEEE Trans. Cybern., 2016, no. 99, pp. 1–14.
Funding
This work was supported by The National Key Research and Development Program of China [2017YFB1304101], Beijing Natural Science Foundation [L172050], Hebei provincial major S&T Research and Development Projects [18277610D], The Fundamental Research Funds for Central Public Welfare Research Institutes [118 009 001 000 160 001], Key Laboratory of Rehabilitation Aids Technology and System of the Ministry of Civil Affairs and Beijing Key Laboratory of Rehabilitation Technical Aids for Old-Age Disability.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
About this article
Cite this article
Li Wang, Lan, Z., Wang, Q. et al. ELM_Kernel and Wavelet Packet Decomposition Based EEG Classification Algorithm. Aut. Control Comp. Sci. 53, 452–460 (2019). https://doi.org/10.3103/S0146411619050079
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411619050079