Abstract
With the aim to solve the problems such as low classification accuracy and weak anti-disturbances in brain–computer interfaces (BCI) of motion imagery , a new method for recognition of electroencephalography (EEG) was proposed in this work, which combined the wavelet packet transform and BP neural network . First, EEG is decomposed by wavelet packet analysis. Then, distance criterion is selected to measure the separable value of the feature frequency bands. Furthermore, the optimal basis of wavelet packet is attained by using a fast search strategy of “from the bottom to the top, from left to right.” The classification feature is extracted by choosing the part wavelet package coefficient, which can attain higher classification evaluation value according to the optimal basis of wavelet packet. And then, the optimal bands are combined with BP neural network. The experimental results show that the proposed method can choose the feature bands of EEGs adaptively, and the highest classification accuracy is 94 %. The correctness and validity of the proposed method is proved. Lastly, establish the virtual robot in MATLAB and use the classification results to control the robot’s arm motion.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Alma SM, David J, Rares B et al (2002) Virtual reality–augmented rehabilitation for patients following stroke. J Phys Ther 82(9):898–915
Burke DP, Kelly SP, De Chazal P et al (2005) A parametric feature extraction and classification strategy for brain-computer interfacing. J IEEE Trans Neural Syst Rehabil Eng 13(1):12–17
Coifman RR, Hauser MVW (1992) Entropy based algorithms for best basis selection. J IEEE Trans IT 38(3):713–718
Fatourechi M, Mason SG, Birch GE (2004) A wavelet-based approach for the extraction of event related potentials from EEG. In: IEEE international conference on acoustics, speech, and signal processing. Montreal: ICASSP, pp 737–740
Furstcheller PG, Muller-Putz GR, Schlogl A et al (2006) 15 years of research at Graz university of technology: current projects. J IEEE Trans Neural Syst Rehabil Eng 14(2):205–210
Furstcheller P, Neuper G (2001) Motor Imagery and direct brain-computer communiction. Proc IEEE 89(7):1123–1134
Huang H, Ingalls T, Olson L et al (2005) Interactive multimodal biofeedback for task-oriented neural rehabilitation. In: Proceedings of the 2005 IEEE engineering in medicine and biology 27th annual conference, pp 2547–2550
McFarland DJ, Anderson CW, Muller KR et al (2006) BCI meeting 2005-workshop on BCI signal processing: feature extraction and translation. J IEEE Trans Neural Syst Rehabil Eng 14(2):135–138
Ren LP, Zhang AH, Hao XH et al (2008) Study on classification of imaginary hand movements based on bands power and wavelet packet entropy. J Chin J Rehabil Theory Pract 14(2):141–143
Vaughan TM (2003) Brain-computer interface technology: a review of the second international meeting. J IEEE Trans Neural Syst Rehabil Eng 11(2):94–109
Virt SJ (2006) The third international meeting on brain- computer interface technology: making a difference. J IEEE Trans Neural Syst Rehabil Eng 14(2):126–127
Wolpaw JR, Birbaumer N, McFarland DJ et al (2002) Brain- computer interface for communication and control. J Clin Neurophysiol 113(6):767–791
Xu AG, Song AG (2007) Feature extraction and classification of single trial motor imagery EEG. J J SE Univ 37(4):629–630
Yang BH, Yan BH, Yan GZ (2007) Extracting EEG feature in brain-computer interface based on discrete wavelet transform. J Chin J Biomed Eng 25(5):518–519
Zhang J, Zheng C, Xie A (2000) Bispectrum analysis of focal ischemic cerebral EEG signal using third-order recursion method. J IEEE Trans Biomed Eng 47(3):352–359
Acknowledgments
Project supported by the National Natural Science Foundation of China (No. 51275101).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Zhejiang University Press and Springer Science+Business Media Singapore
About this paper
Cite this paper
Wang, L., Fu, H., Zhang, Xf., Yang, R., Zhang, N., Ma, F. (2017). An Adaptive Feature Extraction and Classification Method of Motion Imagery EEG Based on Virtual Reality. In: Yang, C., Virk, G., Yang, H. (eds) Wearable Sensors and Robots. Lecture Notes in Electrical Engineering, vol 399. Springer, Singapore. https://doi.org/10.1007/978-981-10-2404-7_8
Download citation
DOI: https://doi.org/10.1007/978-981-10-2404-7_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-2403-0
Online ISBN: 978-981-10-2404-7
eBook Packages: EngineeringEngineering (R0)