Classification of motor imagery tasks for electrocorticogram based brain-computer interface

详细信息    查看全文

• 作者：Fangzhou Xu (1)
  Weidong Zhou (1)
  Yilin Zhen (2)
  Qi Yuan (1)
  
• 关键词：Local binary pattern (LBP) ; Brain ; computer interface (BCI) ; Electrocorticogram (ECoG) ; Motor imagery (MI)
• 刊名：Biomedical Engineering Letters
• 出版年：2014
• 出版时间：June 2014
• 年：2014
• 卷：4
• 期：2
• 页码：149-157
• 全文大小：553 KB
• 参考文献：1. Lotte F, Congedo M, L茅 cuyer A, Lamarche F, Arnaldi B. A review of classification algorithms for EEG-based braincomputer interfaces. J Neural Eng. 2007; 4:R1鈥?3. CrossRef
  2. Vallabhaneni A, Wang T, He B. Brain-computer interface. In: He B, editor. Neural Engineering. US: Springer; 2005. pp. 85鈥?21. CrossRef
  3. Nicolas-Alonso LF, Gomez-Gil J. Brain computer interfaces, a review. Sensors. 2012; doi:10.3390/s120101211 .
  4. Ince NF, Goksu F, Tewfik AH. ECoG based brain computer Interface with subset selection. Biomed Eng Syst Technol. 2009; 25:357鈥?4. CrossRef
  5. Leuthardt EC, Schalk G, Wolpaw JR, Ojemann JG, Moran DW. A brain-computer interface using electrocorticographic signals in humans. J Neural Eng. 2004; 1:63鈥?1. CrossRef
  6. Ball T, Kern M, Mutschler I, Aertsen A, Schulze-Bonhage A. Signal quality of simultaneously recorded invasive and noninvasive EEG. Neuroimage. 2009; 46:708鈥?6. CrossRef
  7. Levine SP, Huggins JE, BeMent SL, Kushwaha RK, Schuh LA, Passaro EA, Rohde MM, Ross DA. Identification of electrocorticogram patterns as the basis for a direct brain interface. J Clin Neurophysiol. 1999; 16:439鈥?7. CrossRef
  8. Liu C, Gaetz W, Zhu H. The stockwell transform in studying the dynamics of brain functions. Conf Proc Pseudo-Differential Operators: Complex Anal Partial Differential Equations. 2010; 205:277鈥?1.
  9. D鈥機roz-Baron D, Ramirez JM, Baker M, Alarcon-Aquino A, Carrera O. A BCI motor imagery experiment based on parametric feature extraction and fisher criterion. Conf Proc Electr Commun Comput. 2012; 257鈥?1.
  10. Zhao H, Liu C, Yu C, Wang H. Channel selection and feature extraction of ECoG-based brain-computer interface using band power. Appl Mech Mater. 2011; doi: 10.4028/www.scientific.net/AMM.44-47.3564 .
  11. Li M, Yang J, Hao D, Jia S. ECoG recognition of motor imagery based on SVM Ensemble. Conf Proc IEEE Rob Biomimetics. 2009; 1967鈥?2.
  12. Ojala T, Pietikainen M, Harwood D. A comparative study of texture measures with classification based on feature distributions. Pattern Recognit. 1996; 29:51鈥?. CrossRef
  13. Ojala T, Pietikainen M, M盲enp盲盲 T. Gray scale and rotation invariant texture classification with local binary patterns. Lect Notes Comput Sc. 2000; 1842:404鈥?0. CrossRef
  14. Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell. 2002; 24(7):971鈥?7. CrossRef
  15. Guo ZH, Zhang L, Zhang D. Rotation invariant texture classification using LBP variance (LBPV) with global matching. Pattern Recognit. 2010; 43:706鈥?9. CrossRef
  16. McFarland DJ, Wolpaw JR. Sensorimotor rhythm-based brain-computer interface (BCI): model order selection for autoregressive spectral analysis. J Neural Eng. 2008; 5:155鈥?2. CrossRef
  17. Paranjape RB, Mahovsky J, Benedicenti L, Koles Z. The electroencephalogram as a biometric. Conf Proc Electr Comput Eng. 2001; 2:1363鈥?.
  18. Huan NJ, Palaniappan R. Neural network classification of autoregressive features from electroencephalogram signals for brain-computer interface design. J Neural Eng. 2004; 1(3):142鈥?0. CrossRef
  19. Mirowski P, Madhavan D, LeCun Y, Kuzniecky R. Classification of patterns of EEG synchronization for seizure prediction. Clin Neurophysiol. 2009; 120:1927鈥?0. CrossRef
  20. Hoffmann U, Garcia G, Vesin JM, Diserens K, Ebrahimi T. A boosting approach to p300 detection with application to braincomputer interfaces. Conf Proc IEEE Neural Eng. 2005; 97鈥?00.
  21. http://www.bbci.de/competition/iii/#data_set_i.
  22. Lai TN, Hinterberger T, Widman G, Schroeder M, Hill J, Rosenstiel M, Elger C, Scholkopf B, Birbaumer N. Methods towards invasive human brain computer interfaces. Conf Proc Adv Neural Inf Process Syst. 2005; 17:737鈥?4.
  23. Hariharan M, Fook CY, Sindhu R, Ilias B, Yaacob S. A comparative study of wavelet families for classification of wrist motions. Comput Electr Eng. 2012; 38:1798鈥?07. CrossRef
  24. Friedmann JH, Hastie T, Tibshirani R. Additive logistic regression: a statistical view of boosting. Ann Statist. 2000; 28:337鈥?07. CrossRef
  25. Friedmann JH. Greedy function approximation: a gradient boosting machine. Ann Statist. 2001; 29(5):1189鈥?32. CrossRef
  26. Manyakov NV, Chumerin N, Combaz A, Hulle MMV. Comparison of classification methods for p300 brain-computer interface on disabled subjects. Comput Intell Neurosci. 2011; 1鈥?2.
  27. Huang A, Zhou W. BLDA approach for classifying p300 potential. Conf Proc Med Biol Eng. 2008; 19:341鈥?.
  28. Hoffmann U, Vesin JM, Ebrahimi T, Diserens K. An efficient p300-based brain-computer interface for disabled subjects. J Neurosci Methods. 2008; 167:115鈥?5. CrossRef
  29. Wei Q, Tu W. Channel selection by genetic algorithms for classifying single-trial ECoG during motor imagery. Conf Proc IEEE Eng Med Biol Soc. 2008; 624鈥?.
  30. Zhao H, Yu C, Liu C, Wang H. ECoG-based brain-computer interface using relative wavelet energy and probabilistic neural relative wavelet energy and probabilistic neural. Conf Proc Biomed Eng Inform. 2010; 873鈥?.
  
• 作者单位：Fangzhou Xu (1)
  Weidong Zhou (1)
  Yilin Zhen (2)
  Qi Yuan (1)
  
  1. School of Information Science and Engineering, Shandong University, Shandong, China
  2. Troops 72465 of PLA, Shandong, China
  
• ISSN：2093-985X

文摘

Purpose In the present study, we propose a novel scheme for motor imagery (MI) classification of multichannel electrocorticogram (ECoG) recordings from patients with medically intractable focal epilepsy. Methods This scheme proposes a combination of the two features which includes autoregressive (AR) model coefficients and local binary pattern (LBP) operators. It can provide spatial resolution and angular space information. Then the gradient boosting (GB) in conjunction with ordinary least squares (OLS) algorithm is employed as the classifier to improve the performance of MI classification for ECoG based Brain Computer Interface (BCI) system. Results Experimental results on the BCI Competition III data set I indicate that the novel method has excellent performance and yields a cross-validation accuracy of 88.8% and accuracy of 93%, respectively. Conclusions From the experimental results and comparative studies, we can infer that the scheme may serve as a good MI classification tool for a better tradeoff between the classification accuracy and computational complexity.