The Identification of EEG Feature Evoked by Imaginary Movement

Abstract:

Aiming to the ERD/ERS phenomenon of left-right hand imaginary movement, this paper presents a method of wavelet transform combined with statistical analysis to extract EEG features evoked by imaginary movement. And the features were classified using the support vector machine based on RBF kernel and cross-validation accuracy (CVA) method. The results have shown that this method can perform effectively to extract features and reflect ERS and ERD characteristics of EEG signal. The accuracy of classification can reach 90% within the time costing 3.5 seconds. The highest signal to noise ratio is 1.445, and the maximum mutual information is 0.645bit. The results can meet the real-time brain-computer interface system.

• Periodical: Applied Mechanics and Materials (Volumes 427-429)
• Pages: 2059-2063
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.427-429.2059
• Online since: September 2013
• Authors: Xiao Yan Qiao*, Chun Hui Wang
• Keywords: Imaginary Movement, Statistical Analysis, Support Vector Machine (SVM), Wavelet Transform (WT)

References

[1] Yang Licai, Li Baimin and Li Guanglin, A Review of Brain-Computer Interface Technology, Acta Electronic Sinica, vol. 7, pp.1234-1241, (2007).

[2] Wu Yazhou, Wu Baoming and He Qinghua, Actual research on brain-computer interface system based on electroencephalography, Chinese Journal of Clinical Rehabilitation, vol. 1, pp.147-150, (2006).

[3] Quadrianto N, GuanCunTai and Dat TH, Sub-band Common Spatial Pattern (SBCSP) for Brain-Computer Interface, 2007 3rd International IEEE/EMBS Conference on Neural Engineering, Piscataway, NJ, USA: IEEE, 2007, pp.219-225.

DOI: 10.1109/cne.2007.369647

[4] Wu Wei, Gao Xiaorong and Gao Shangkai, One-versus-the-best (OVR) algorithm: an extension of common spacial patterns (CSP) algorithm to muti-class case, Proceedings of 27th Annual International Conference of the Engineering in Medicine and Biology Society, Piscataway, NJ, USA: IEEE-EMBS, 2005, pp.2387-2390.

DOI: 10.1109/iembs.2005.1616947

[5] Wang Yanjing, Qiao Xiaoyan and Li Peng, Classification of motor imagery task based on wavelet packet entropy and support vector machines, Chinese Journal of Scientific Instrument, vol. 12, pp.2729-2735, (2010).

[6] A.I. Belousov, S.A. Verzakov, J. von Frese. A flexible classification approach with optimal generalization performance: support vector machines, Chemometrics and Intelligent Laboratory Systems, vol. 64, 2002, p.15– 25.

DOI: 10.1016/s0169-7439(02)00046-1

[7] Tie Shengli, Applying wavelets transform and support vector machinenext term for copper clad laminate defects classification, Computer and Industrial Engineering, vol. 56, pp.1154-1168, (2009).

DOI: 10.1016/j.cie.2008.09.018

[8] BCICompetition. http: /ida. first. fraunhoferde/projects/bci/competition.

[9] Christa Neupera, Reinhold Scherer and Selina Wriessnegger, Motor imagery and action observation: Modulation of sensorimotor brain rhythms during mental control of a brain–computer interface,. Clinical Neurophysiology, vol. 120, p.239–247, (2009).

DOI: 10.1016/j.clinph.2008.11.015

[10] Qiao Xiaoyan, Wang Yanjing, Feature Extraction and Classifier Evaluation of EEG for Imaginary Hand Movements, Natural Computation (ICNC), 2010 Sixth International Conference on, Yantai, Shandong, China: IEEE, vol. 4, 10-12 Aug. 2010, pp.2112-2116.

DOI: 10.1109/icnc.2010.5582453

[11] G. Pfurtscheller G.R. MullerPutz,A. Schlögl,B. Graimann,R. Scherer,R. Leeb et al. 15 years of BCI research at Graz university of technology, IEEE transaction on neural systems and rehabilitation engineering, june 2006, vol. 14, No. 2, pp.205-209.

DOI: 10.1109/tnsre.2006.875528